2.1.1 Tool of Analysis: Governing Knowledge Commons Framework

To describe the MIDATA cooperative in a structured and detailed way, the remainder of this chapter will apply the Governing Knowledge Commons (GKC) framework to MIDATA. Brett Frischmann, Michael Madison, and Katherine Strandburg developed the GKC framework, drawing inspiration from Elinor Ostrom and her colleagues’ work on the institutional analysis and development framework (Reference OstromOstrom, 1990; Reference Frischmann, Madison, Strandburg, Frischmann, Madison and StrandburgFrischmann, Madison, and Strandburg, 2014; Reference Strandburg, Frischmann, Madison, Frischmann, Strandburg and MadisonStrandburg, Frischmann, and Madison, 2017). This framework allows researchers to analyze “institutionalized community governance of the sharing and, in some cases, creation, of information, science, knowledge, data, and other types of intellectual and cultural resources” (Reference Frischmann, Madison, Strandburg, Frischmann, Madison and StrandburgFrischmann, Madison, and Strandburg, 2014, 3). In combination with Helen Nissenbaum’s theory that understands privacy as contextual integrity (Reference NissenbaumNissenbaum, 2010), the GKC framework is useful when examining how individuals maintain privacy and govern their own health data cooperative. Broadly, the framework considers the background environment, attributes, governance, patterns, and outcomes of knowledge commons. The remainder of this chapter will follow the structure of the GKC framework to ease comparison across the different case studies of this and earlier volumes of the knowledge commons book series (Reference Strandburg, Frischmann, Madison, Frischmann, Strandburg and MadisonStrandburg, Frischmann, and Madison, 2017, 16–17).

At present, MIDATA is in the buildup phase. Several small research projects, as presented later, contribute to the testing and refinement of MIDATA. This chapter is part of an ongoing (2018–2021) health ethics and policy research project at ETH Zürich, Switzerland, where we aim to develop further the existing governance model of MIDATA. Our main purpose in this research is to create a systemic oversight model for MIDATA (described later) that is considered trustworthy by the general public and MIDATA members. In this research we engage with governance theory, law, and policy, and will conduct interviews with different stakeholders, such as researchers who work within the cooperative, members of the cooperative, and members of the general public. For this chapter we gathered background information by interviewing MIDATA co-founder Ernst Hafen. For the interview we developed questions that follow the content of the GKC framework and Nissenbaum’s privacy theory. In addition, we examined the statutes of MIDATA as well as further policy and administrative documents of the cooperative. The advantage of applying the GKC framework and insights from privacy theory as contextual integrity at this stage is the possibility to leverage the perspective the framework provides to inform MIDATA’s ongoing development. Applying the GKC framework to MIDATA can help us better understand how MIDATA processes and structural components contribute to the community governance of MIDATA. The systematic design of the GKC framework allows us to dissect MIDATA to unfold the involved attributes, the present governance structure, and anticipated outcomes. In addition, the theory of privacy as contextual integrity can help us to improve the governance processes and structures that apply to privacy within MIDATA.

2.2.1 MIDATA Resources

The resources pooled in the MIDATA cooperative are copies of account holders’ personal data. Such data can be transferred to the account by the account holder him/herself; or in some cases apps use MIDATA to store data, and account holders using such an app can allow the data to be deposited in to their MIDATA accounts directly. Accessing copies of personal data has been simplified within the European Union with the newly established European Union’s General Data Protection Regulation. This regulation emphasizes in Article 20 that individuals have the right to copies of their data. This right applies to EU residents, and non-EU residents can ask for copies of data stored by companies based within the EU (European Parliament Council of the European Union, 2016). It is anticipated that this European regulation will supportively affect the data transfer processes for MIDATA, even though the regulation does not apply in Switzerland as Switzerland is not an EU member state (Reference Ngwa and HafenNgwa and Hafen, 2017). Swiss residents can make use of the GDPR when they request data that is stored within the EU.

The allergy app Ally Science is an example of an app that stores data on MIDATA. Launched by Bern University of Applied Sciences and University Hospital Zurich, Ally Science is part of a research project to collect pollen allergy symptoms data in combination with location data. Thereby, the study investigates pollen allergies in Switzerland (MIDATA Genossenschaft, 2019a). If the app user has no MIDATA account, the app user is asked to open a MIDATA account before s/he uses the app. By July 2018, 8,100 app users had registered (Reference HafenHafen, 2018). Another use case example is a research study involving multiple sclerosis patients. Study participants use an app called MitrendS to capture their neurological development over time. Generally speaking, each citizen generates a huge amount of data that can be stored in MIDATA accounts so that each citizen can contribute to the development of the cooperative’s resource pool (Reference Mòdol, Riemer, Schellhammer and MeinertMòdol, 2019).

2.2.2 MIDATA Account Holders, Cooperative Members, and the Swiss Community

Because the cooperative model of MIDATA is designed to be regional, MIDATA is open to any person residing in Switzerland. To open an account on MIDATA, one does not need to be a member of the cooperative. Yet, if a person would like to actively participate in the governance of MIDATA, a community member needs to become a cooperative member for a fee of 40 CHF. The cooperative has an altruistic motivation that goes beyond the MIDATA community itself and seeks to benefit the general society, and this is evident in the objectives outlined later.

2.2.3 Goals and Objectives of MIDATA

The overarching goal of MIDATA is to establish regional, member-owned data cooperatives that contribute to research and ultimately to the benefit of society via their stored data. In more detail and as stated by Article II of the MIDATA statutes, the objectives are:

1. (1) “The Cooperative pursues as a non-profit organization the following objectives:

   1. (a) it operates a secure IT platform (‘MIDATA platform’) for storage, management, and sharing of personal data of any kind, in particular health and education data, and to provide related services;

   2. (b) it makes the MIDATA platform available to natural persons (members and non-members) who may use the platform as personal data account holders (‘account holders’);

   3. (c) it promotes broad Cooperative membership among account holders, thus allowing them to partake in the governance of the Cooperative, and it helps members pursue common interests;

   4. (d) it promotes the digital self-determination of the population by enabling account holders to use their personal data as self-determining agents and according to their wishes, in particular to support research purposes;

   5. (e) it promotes the collective interests of the account holders and it enables the utilization of their personal data as a common resource. This is achieved by enabling individual account holders to accept requests for the analysis of their data and to give explicit informed consent for the secondary use of their personal data by third parties in return for an economic remuneration to the cooperative;

   6. (f) by providing the MIDATA platform, it fosters the development of an innovative ecosystem in which third parties can offer data-based services to the account holders;

   7. (g) it promotes medical research projects and projects that aim to realize a fair digital society and that promote the digital self-determination of the population; and

   8. (h) it employs the scientific results and income derived from the secondary usage of personal data in the framework of the aforementioned objectives.

2. (2) With its operative and commercial activities, the Cooperative strives to achieve a positive effect upon society and the environment.

3. (3) The Cooperative may engage in all activities that are directly or indirectly related to its purpose.

4. (4) The Cooperative may support the founding of cooperatives of equal purpose in Switzerland and abroad, and it may form a federation of cooperatives together with them.

5. (5) The Cooperative may establish branches and subsidiaries in Switzerland and abroad, hold interests in other companies in Switzerland and abroad, and acquire, hold and sell real estate.” (MIDATA Genossenschaft, 2017, 2,3)

Key values represented by the objectives are data security, being open to all people, promotion of cooperative membership, promotion of digital self-determination, promotion of collective interest, fostering innovation and medical research, and re-investment in the goals of the cooperative. Together these values eventually lead into the overarching aim to achieve a positive effect on society and environment. Furthermore, to build a network of cooperatives, MIDATA may help to facilitate similar cooperatives. To finance itself, the cooperative may engage in financial investment activities.

All key values are relevant to this cooperative’s character, but we consider promotion of digital self-determination the one value that makes this cooperative distinctive. As we presented in the introduction of this chapter, outside of the cooperative model, private individuals’ ability to determine how their personal data is used is limited, if not impossible. Therefore, MIDATA aims to foster digital self-determination as one of the key incentives for members of the general public to participate in MIDATA and eventually become MIDATA cooperative members. Objective 1 (d) underlines this clearly by promoting the personal use and free choice over what one wishes to do with his/her data, focusing in particular on research.

When we compare the MIDATA objectives to the cooperative principles as stated by the International Co-operative Alliance (Voluntary and Open Membership; Democratic Member Control; Member Economic Participation; Autonomy and Independence; Education, Training, and Information; Cooperation among Cooperatives; and Concern for Community), it becomes clear that MIDATA is in line with the cooperative tradition (International Co-operative Alliance, 2019). Based on the similarity between the MIDATA cooperative values and general cooperative principles, and given the prevalence of cooperative membership already present in Switzerland, it seems likely people will easily familiarize themselves with the governance principles of MIDATA as they participate in MIDATA activities. This should facilitate easy access and participation in MIDATA. Nevertheless, MIDATA’s focus on scientific data is clearly different from grocery trading and car sharing. It is essential to educate participants so they are equipped to contribute to the MIDATA governance in a meaningful way. Yet, MIDATA participants can build on their previous familiarity with cooperatives in other areas of their lives.

As MIDATA focuses at present on healthcare and public health research, data stored within MIDATA may contribute to the improvement of health for all. Furthermore, it is anticipated that the cooperative as a whole could advance public literacy and public control in the field of digital self-determination. These two aspirations together comprise the key value of knowledge production within the cooperative.

3.3.1 A Brief History of Anxiety

Culture has shaped how people have understood and treated anxiety throughout history (Reference HorwitzHorwitz, 2013). The very language we use to describe the problem is rooted in cultural lore: The word “panic” derives from the Greek god Pan, whose battle cry was said to fill his enemies with uncontrollable fear. In ancient Greece, soldiers who experienced panic in battle were often regarded as cowards and imprisoned or executed. Some historians credit Aristotle (384–320 BCE) for taking the first step toward understanding anxiety as a pathological condition. In exploring the idea of fear, he wrote, “For the man who is by nature apt to fear everything, even the squeak of a mouse, is cowardly with a brutish cowardice, while the man who feared a weasel did so in consequence of disease.” In other words, fear can sometimes be healthy and warranted and other times a sign of illness. (We can surmise that in Aristotle’s time, mice were generally considered a rational source of fear, whereas weasels were not.)

Other Greek philosophers made some of the earliest and most enduring contributions toward Western understandings of anxiety. Hippocrates (460–367 BCE), for example, sought to understand medical disorders by observing his patients in a systematic, scientific manner. This process led him to develop a system for classifying mental disorders, including anxiety. Today, a similar classification system called the Diagnostic and Statistical Manual (DSM) is widely used in the medical profession to identify mental health disorders (Reference GhinassiGhinassi, 2010). Hippocrates conjectured that the key to treating anxiety was in achieving a kind of harmony between the body and mind (Reference Kleisiaris, Sfakianakis and PapathanasiouKleisiaris, Sfakianakis, and Papathanasiou, 2014).

Socrates (470–399 BCE) expanded the set of tools that experts had to investigate anxiety. The Socratic Method, a process of deeply questioning one’s underlying assumptions, is perhaps his most lasting methodological contribution. Like Hippocrates, Socrates also believed that the key to mental health had to do with the relationship between the body and the mind. Understanding this relationship, he believed, required not only physical examination but also introspection on the part of the patient. The idea is captured well in his famous injunction to his followers, “know thyself” (Reference GhinassiGhinassi, 2010). Plato (427–347 BCE) believed that anxiety was rooted in incorrect or distorted beliefs about the world. His solution was straightforward: educating sufferers about their erroneous beliefs, and through persistent reminding and reasoning, attempts to alter those beliefs.

Arguably, even more nuanced insights about mental health appear in Buddhist teachings from the fifth century BCE. In his teachings, Siddhartha Gautama (The Buddha) explains that people fundamentally misperceive the true nature of the world. The path away from anxiety and other afflictions, he explains, lies in gaining an accurate view of reality as it is, rather than how we imagine it to be. Buddhist traditions usually focus on better aligning the body and mind to gain this clearer view. As Thich Nhat Hanh, a widely known Vietnamese Buddhist master, explains, “Wrong-thinking causes us to see the world in an upside-down way. Our mind is often thinking about one thing while our body is doing another. Mind and body are not unified.”

The Middle Ages, which lasted roughly from the year 476 to 1000 BCE, saw a retreat from the scientific methods developed in ancient Greece in favor of the supernatural. In some cultures, the belief emerged that mental disorders are evidence of demonic possession. This idea is likely the historical root of the stigma that many sufferers of anxiety and depression experience today. In some cultures, the notion of demonic possession persists.

The European renaissance sparked a return to ancient insights. In the fifteenth century, for instance, Descartes developed the idea of “mind-body dualism” – the notion, as Descartes described it, that the mind and the body “compose a certain unity.” This insight led to the modern recognition of the fact that the mind and the body influence each other – “bidirectionality” – a core principle of contemporary treatment. These ideas were not new, of course. The Latin phrase “mens sana in corpore sano” (“a healthy mind in a healthy body”) dates to the second century.

Psychology, the modern scientific study and treatment of behavior and the mind, took root and flourished in the late nineteenth and early twentieth centuries. Some leaders in the field, such as Sigmund Freud and Carl Jung, focused heavily on the subjective experiences of patients. Freud believed, for instance, that the roots of anxiety, depression, and related mental health disorders lay in repressed sexual energy. Although this view is not widely credited today, Freud made a lasting contribution to the modern understanding of anxiety by classifying it into different forms: generalized anxiety, panic disorders, phobias, and obsessions (Reference HorwitzHorwitz, 2013).

Others in the then-emerging field searched for objective sources of information on the disorder. Ivan Pavlov (1849–1936) illustrated that anxiety responses could be conditioned in animals – a discovery that suggested people might develop anxiety disorders as a learned response to life experiences. Pavlov’s work inspired the field of behavioral psychology, which explores the theory that people acquire mental conditions entirely through learning. John Watson (1878–1959), Rosalie Rayner (1899–1935), and B.F. Skinner (1904–1990) are widely known names in this field.

In the 1950s, researchers challenged the notion that anxiety is solely a learned behavior. These experts argued that cognition, or how one sees and appraises the world, must play a role too. George Kelly (1905–67) advanced the idea that people perceive the world as a series of mental constructs. Mental disorders may arise when these constructs are inaccurate. This view seems to align remarkably well with the core teachings of Buddhist philosophy, as well as Plato’s teachings, both mentioned earlier. Recent research indicates that life experiences, including stressful environments and incidents, particularly in childhood, can “activate” the disorder.

Cognitive-behavioral therapy (CBT), one of the most effective techniques to treat anxiety today, is grounded in the idea that anxiety is a self-reinforcing behavior that stems from our misunderstanding of the world. Patients who undergo CBT treatment learn about common types of cognitive distortions, and then learn to spot these distortions in their thinking. For instance, some people who suffer from anxiety tend to think about future events in binary or black-and-white terms. In the mind of a person experiencing anxiety, the results of a routine blood test for cholesterol, for instance, will reveal either perfect health or imminent death. The simple act of recognizing this form of thinking and placing a label on it has been shown to drain it of its power.

In the 1950s, the American Psychiatric Association published the first edition of the DSM. Now in its fifth edition, the DSM is the primary tool that medical professionals use to diagnose mental health disorders, including anxiety. Some critics of the modern psychological establishment argue that the DSM’s focus on classification implies a level of clarity and precision to the diagnosis of mental health disorders that does not exist. This line of criticism is mostly academic, however, and removed from the day-to-day business of treating people with mental health disorders.

Alongside CBT, another important set of tools for treating anxiety are drugs. People have used chemicals derived from plants to manage stress and anxiety for millennia. Alcohol, one of the earliest such substances, remains one of the most popular. Opium, a drug derived from a type of poppy plant, has been used as a sedative at least since 4000 BCE. In the late nineteenth century, a chemist working at the Bayer Company successfully diluted the active molecule in opium – diacetylmorphine. Bayer branded the chemical as “heroin” and commercialized it in 1898. The drug’s dangerousness and addictive qualities were evident within just a few years of public use. Opiates were eventually replaced by barbiturates, another depressant, which were developed chiefly by a German chemist and Nobel Prize winner named Adolf von Baeyer.

In the 1950s, the pharmaceutical company Smith-Kline began selling a drug it called Thorazine. The drug’s popularity for treating mental health disorders fueled research into the development of new drugs designed to address specific disorders. The first drug that was developed specifically to target anxiety was called Miltown. Although highly effective, it was, unfortunately, also highly addictive. Continued research led to the creation of benzodiazepines, including diazepam (Valium) and alprazolam (Xanax). These drugs are often prescribed to treat acute episodes of panic, but like earlier drugs, they can be highly addictive. In the 1970s, Eli Lilly and Company introduced Fluoxetine (Prozac), a new kind of medicine called a selective serotonin reuptake inhibitor (SSRI). Approved by the FDA in 1987, the drug remains widely used and highly regarded, along with other SSRIs, such as Zoloft, Paxil, Luvox, Celexa, and Lexapro. SSRIs are the most commonly prescribed drugs in the United States and by far the frontline defense against anxiety. Despite the significant advances in drug development that took place in the twentieth century, very few new drugs have been developed to target anxiety since the 1990s.

Recent studies have shown that today, drugs (serotonin inhibitors) and CBT are the two most effective and standard tools to manage clinical anxiety [4]. Several complementary and integrated health treatments have also been shown to reinforce the benefits offered by conventional medical treatment. These include stress and relaxation techniques, yoga, meditation, and acupuncture [5]. Getting adequate sleep, regular exercise, maintaining a healthy diet, having a robust social support system, and living with low levels of stress are also important [6]. For people who have access to adequate mental health care, educational resources, and the ability to follow a beneficial lifestyle, anxiety can be highly manageable. Unfortunately, as discussed in the following section, there is a shortfall in access to mental health care.

3.3.2 The Patient Context

Nearly all anxiety disorders involve intense feelings of fear and the anticipation of imminent harm (Reference Hilty and MucicHilty and Mucic, 2016; Reference RachmanRachman, 2020). A short review of several types of anxiety shows subtler aspects of the problem. Under the heading of Anxiety, the DSM identifies the following: (i) generalized anxiety disorder, (ii) panic disorder, (iii) social anxiety disorder, (iv) obsessive-compulsive disorder, (v) post-traumatic stress disorder, and (vi) specific phobias:

1. (i) In generalized anxiety disorder, feelings of worrying and fear permeate everyday life. Sometimes, these feelings are tied to real causes for worry, but they are disproportionately intense. (Recall Aristotle’s mouse.) Other times, the feelings may be disconnected from any cause that the sufferer can identify – a kind of free-floating dread. These feelings are often accompanied by physical discomfort, such as muscle tension, restlessness, queasiness, and nausea. Those with generalized anxiety disorder are focused heavily on the future, both near- and long-term, and unable to tolerate feelings of uncertainty (Reference RachmanRachman, 2020).

2. (ii) Panic disorders, another class of anxiety disorder, are typified by intense physical and mental episodes of uncontrollable fear brought on by a perceived threat that typically does not exist. These episodes are different from the chronic worrying and fear that generalized anxiety disorder brings on: they are more physically intense and often mistaken by sufferers for heart attacks.

3. (iii) Social anxiety is identified by unwarranted feelings of embarrassment and self-consciousness. Unsurprisingly, people who suffer from this problem often isolate themselves.

4. (iv) Obsessive-compulsive disorder is characterized by repetitive or compulsive behaviors, such as hoarding, arranging objects in specific patterns, and extreme avoidance of germs.

5. (v) Another manifestation of anxiety, post-traumatic stress disorder (“PTSD”), has received a wealth of attention in the media because soldiers often experience it. Unlike generalized anxiety disorder or panic disorders, which inherently focus on the future, this problem is heavily focused on the past. Often a traumatic experience gives rise to nightmares and related, intensely upsetting memories.

6. (vi) Lastly, are specific phobias – the experience of anxiety symptoms brought on by certain situations or objects.

As mentioned in the introduction, anxiety is the most common mental health disorder in the United States. According to the Anxiety and Depression Association of America, 40 million adults age 18 or older, or about 18.1 percent of the population, is affected by anxiety every year [1]. Although the United States has the highest rate of anxiety in the world, the disorder is prevalent elsewhere. Interestingly, there does not seem to be a correlation between anxiety and industrialization: rates are very high in France, Colombia, and Lebanon. China and Nigeria, meanwhile, have relatively low rates. Moderate evidence suggests that culture and context impact how often the problem arises. Poverty correlates with higher rates of generalized anxiety disorder, for instance.

Recent research indicates that life experiences, including stressful environments and incidents, particularly in childhood, can “activate” the disorder (Reference GhinassiGhinassi, 2010). Studies have shown that the development of anxiety can be mitigated, however, by positive protective factors. Chief among these are parents who are warm and sensitive to the feelings of a child, and who impart upon the child an internal “locus of control” – a feeling that the child has control over his or her life. Although childhood experiences seem to be foundational, anxiety disorders can arise at any age in a person’s life. The average age of onset for generalized anxiety disorder, for instance, is thirty-one. As mentioned in the introduction, it is estimated that the total annual cost of anxiety runs in the neighborhood of $47 billion annually.

One of the reasons that anxiety rates are soaring in the United States could be the fact that the problem is widely under-treated (U.S. Department of Health and Human Services, 2018). One reason for this is stigma: Many people with anxiety are reluctant to seek treatment because they believe others (family members, neighbors, etc.) will judge them poorly if they learn they suffer from anxiety. As with so many aspects of anxiety, the perception of stigma varies greatly by age, ethnicity, religious, and other cultural lines.

In addition to stigma, recent studies have shown that in many areas of the United States, there is a workforce shortage in child psychiatry and in other behavioral health practitioners (Health Resources and Services Administration/National Center for Health Workforce Analysis, 2015). The problem of access is particularly acute in rural areas: A recent study found that 65 percent of non-metropolitan counties do not have a single psychologist, and 47 percent of non-metropolitan areas do not have a single psychologist (Reference Andrilla, Holly, Patterson, Garberson, Coulthard and LarsonAndrilla, et al., 2018). This problem is likely to worsen. The U.S. Department of Health and Human Services has projected that by the year 2025 there will be shortages of between 6,080 and 15,400 psychiatrists; between 8,220 and 57,490 clinical, counseling, and school psychologists; and as many as 26,930 mental health counselors (Health Resources and Services Administration/National Center for Health Workforce Analysis, 2015). Closely tied to the access problem is the cost of mental health care: Many people with anxiety cannot afford treatment.

3.3.3 Technological Contexts

3.3.4 The Legal and Regulatory Landscape

The emerging therapy chatbot industry is taking form against a complicated patchwork of law and regulations. This policy framework significantly influences how these technologies are developed, funded, and provided. It is important to note that the areas highlighted here are simply the most visible and may not provide a complete picture of the laws and regulations relevant to every therapy chatbot, however.

4.2.1 The Value of Analytics

The advent of new technologies and analytical techniques are enabling the proliferation of data and information within higher education institutions. Reference Goldstein and KatzGoldstein and Katz (2005, 11) explain that “the challenge [to colleges and universities] is no longer the lack of access to timely information”; it is the ability to make actionable decisions based on available information. In the early aughts, universities began to develop capacity for what was then called “academic analytics.” Like business intelligence, academic analytics is the use of various technological systems and applications to analyze accessible institutional data in support of decision-making.

Much of the capacity-building done in support of academic analytics has led to additional analytic practices to serve various ends, in part due to function creep. Most prominent among these practices is the learning analytics movement. Since 2010, institutions have methodically worked to make data about students once “unseen, unnoticed, and therefore unactionable” to be visible and analyzable (Reference Bienkowski, Feng and MeansBienkowski, Feng, and Means, 2012, ix). Defined, learning analytics is “the interpretation of a wide range of data produced by and gathered on behalf of students in order to assess academic progress, predict future performance, and spot potential issues” (Reference Johnson, Smith, Willis, Levine and HaywoodJohnson et al., 2011, 28). A driving goal of learning analytics is to “tailor educational opportunities to each student’s level of need and ability” (Reference Johnson, Smith, Willis, Levine and HaywoodJohnson et al., 2011, 28), but learning analytics is not just about learners: it is also about the learning context and can be used to “assess curricula, programs, and institutions” (Reference Johnson, Smith, Willis, Levine and HaywoodJohnson et al., 2011, p. 28). To a lesser extent than learning analytics, institutions have also begun using their information infrastructures to mine and analyze data about faculty performance and productivity (see Reference FlahertyFlaherty, 2016; Reference PatelPatel, 2016).

Why are higher education institutions pursuing analytics (academic, learning, faculty, or otherwise)? Reference Campbell, DeBlois and OblingerCampbell, DeBlois, and Oblinger (2007, 42) present analytics as a sort of salve for higher education, writing that “academic analytics is emerging as a new tool that can address what seem like intractable challenges.” As in other contexts, institutional actors and higher education pundits have applied powerful metaphors to express – and influence – the role of data mining at the university level (Reference Stark and HoffmannStark and Hoffman, 2019). Some argue that the data and information institutions can aggregate and analyze is akin to valuable natural resources, like oil and gold, that they have social, political, and economic value (see Reference Mayer-Schönberger and CukierMayer-Schönberger and Cukier, 2014; Reference WattersWatters, 2013). Proponents of analytics argue that the insightful information they create can help institutions defend themselves against mounting accountability pressures and provide useful insights regarding resource usage in languishing economic times (Reference Prinsloo, Slade, Menon, Terkla and GibbsPrinsloo and Slade, 2014).

4.2.2 Competing Interests

The turn toward data analytics in higher education raises particular questions about the effects caused by an increasingly data-driven, technocratic institution (Reference Slade and PrinslooSlade and Prinsloo, 2013). Maturing institutional data infrastructures enable the administrative surveillance of researcher productivity, instructional methods, and the day-to-day life of students, which in turn allow for granular reforms of programs, practices, and people – all in the name of institutional effectiveness (Reference SelwynSelwyn, 2014; Reference WilliamsonWilliamson, 2018). Reflecting on this point, Reference JohnsonJohnson (2016, 27) argues:

It could be that data analytics privilege bureaucratic and politically expedient outcomes in ways that suppress what is otherwise “educationally desirable” (Reference Slade and PrinslooSlade and Prinsloo, 2013), including developing just educational systems that support student autonomy and well-being (Reference Rubel and JonesRubel and Jones, 2016). Important questions emerge: Who has the power to wield institutional data, to what ends are analytics directed, and whose interests are served (or ignored)? Reference KitchinKitchin (2014, 165) reminds us that “there is a fine balance between using data in emancipatory and empowering ways, and using data for one’s own ends and to the detriment of others, or in ways contrary to the wishes of those the data represent.”

Government actors, institutional administrators, parents and guardians, and, among others, companies who develop and participate in educational analytics all have varying interests in maximizing value from analyzable data (Reference FergusonFerguson, 2012; Reference Rubel and JonesRubel and Jones, 2016). Such stated benefits include increases in academic success for students, but analytics also enable others to gain financial, social, and reputational advantages.

Consider the following examples of plausible conflicts of interests. Administrators want to decrease time-to-degree measures and increase graduation rates. One method may be to use analytics to direct students to enroll in academic programs or courses for which they meet the threshold for predicted success, say 75 percent. Students share the same goals, but forcing them down an academic path not of their choosing will not benefit them if they find their future careers to be dull and uninteresting. Where faculty are concerned, analytics may enable tenure and promotion committees to do peer-institution comparisons of research output and impact, which help them to make quicker recommendations, in addition to strategically build a core faculty according to standardized metrics. However, these analytics are decontextualized and limited; tenure and promotion candidates may not be provided the opportunity to tell a complete story about their body of work. These competing interests highlight the fact that data and information are not neutral artifacts, but instead they are “cooked” with the motivations of those who wield data and analytic tools (Reference Bowker and GitelmanBowker, 2013).

4.2.3 The Appropriate Flow of Information

When the appropriate flow of information changes, and those changes run counter to normative expectations, privacy is put at risk within a given context (Reference NissenbaumNissenbaum, 2010). With higher education analytics, the creation of new information flows – many of which contain identifiable data – and the alteration of existing flows to support analytic practices have raised privacy concerns, primarily but not exclusively regarding students (Reference Pardo and SiemensPardo and Siemens, 2014; Reference Rubel and JonesRubel and Jones, 2016). The problem with higher education analytics is that all of these parts are affected in some way by emerging analytic infrastructures, related practices, and changes in who is able to access and use data – which are indubitably affected by shifting politics and administrators’ neoliberal interests (Reference HeathHeath, 2014). Some existing informational norms are, therefore, uncapable of providing clear direction in this era of analytics. As a result, institutional actors may find themselves making sensitive, and often critical, data privacy decisions based on their own personal values and ethical judgement. For the purposes of this chapter, we focus on institutional researchers whose very role dictates that they access, manage, and analyze an array of data to inform institutional practices.

4.3.1 Downstream Effects, Impacting Midstream Practice

There is a need to better understand how higher education’s information workers, like institutional researchers, make sense of their moral practices as they implement data analytics into important decision-making strategies. Instead of looking at downstream effects and then shining the proverbial light after the fact, there is a need to look at – and influence – the design of ethically sensitive data technologies and practices closer upstream. These efforts are crucial for identifying problems before they are baked into socio-technical data analytics systems and individuals are made into and considered as data (Reference Jones and McCoyJones and McCoy, 2018). We argue that the socio-technical integration research (STIR) method can lead to positive upstream engagement and useful modulations at the midstream level.

STIR enables research practitioners – laboratory scientists, engineers, technologists, and information professionals – to consider perspectives from the humanities. STIR projects pair practitioners with embedded social scientists who together work to “unpack the social and ethical dimensions of research and innovation in real time and to document and analyse the results” (Fisher, 2010, 76). These partnerships enable researchers to study the practices of their research practitioner partners, while engaging them in conversations that explore the societal and ethical dimensions of their work. Surfacing these issues provides the conditions necessary for research practitioners to reconsider their efforts and make midstream modulations that reduce downstream harms.

4.3.2 Socio-Technical Awareness

During their time together, the STIR researcher takes the opportunity to move the practitioner toward “reflexive awareness,” or an attentiveness to “the nested processes, structures, interactions, and interdependencies, both immediate and more removed, within which they operate” (Reference Fisher, Mahajan and MitchamFisher, Mahajan, and Mitcham, 2006, 492). Such awareness provides the conditions necessary for the practitioner to consider one’s socio-political position, usage of resources, ethical reasoning, among other things, which can give rise to “goal-directed” (Reference Fisher, Mahajan and MitchamFisher, Mahajan, and Mitcham, 2006, 492) modulations that directly impact current practices. To build toward this opportunity for change, the researcher structures discussion protocols around these basic questions, which are asked in relation to a specific practice:

1. 1. What are you doing?

2. 2. Why are you doing it?

3. 3. How could you do it differently?

4. 4. Who might care?

The first question establishes the particulars of a practice (e.g., cleaning a laboratory table with disinfectant or developing an algorithm), while the second prompts the practitioner to take up the underlying justification(s) for the action. Question three begins to nudge the practitioner toward reflexivity by providing the intellectual time and space to consider alternative ways of doing and other justificatory reasons. The fourth and final question stimulates the practitioner to reflect on the present and proposed altered practice by considering relevant stakeholders and downstream effects thereon.

4.3.3 Modulations in Practice

There are three stages of identifiable modulations: de facto, reflexive, and deliberate. With de facto modulations, research data indicates that socio-technical integration occurs, but the research participant does not actively reflect on the integration because there is no incentive to do so. Reflexive modulations by participants arise because of heightened awareness of socio-technical considerations brought about by working with the researcher. In these cases, participants explicitly notice how social influences (e.g., actors, politics, values, resources, etc.) interact with a given practice. At the deliberate modulation stage, participants begin to act on their reflexive modulations. They take stock of their heightened awareness of the socio-technical milieu to plan strategies, curate resources, and make changes in their practices. Such changes may simply make their current practice more efficient and effective, and this would be a first-order deliberate modulation. But if the participant makes changes to alter the goals, objectives, and assumptions of the project due to enhanced social sensitivity, then these changes would be second-order deliberate modulations. In the remainder of this chapter, we discuss our work using STIR to study an institutional research practitioner and the participant’s privacy practices in praxis.

4.3.4 Joining STIR with Institutional Grammar

We integrated the STIR method (Reference Fisher, Mahajan and MitchamFisher, Mahajan, and Mitcham, 2006; Reference Fisher, Schuurbiers, Doorn, Schuurbiers, van de Poel and GormanFisher and Shuurbiers, 2013) and Reference Crawford and OstromCrawford and Ostrom’s (1995) institutional grammar for identifying rules-in-use as expanded to address information privacy concerns (Reference Sanfilippo, Frischmann and StrandburgSanfilippo, Frischmann, and Strandburg, 2018). The STIR approach was used to probe the research participant into considering and acknowledging the implicit socio-technical characteristics that guided the participant’s practice and those within the participant’s office, and with the intention that these have been made explicit that they would lead to identifiable modulations in the participant’s privacy practices. Institutional grammar’s rules-in-use were used to assess rules such as policies and laws, norms that govern privacy practices in institutional research, and strategies that shape the privacy practices of institutional researchers.

4.3.5 Study Design

The study’s participant was a single institutional researcher at a mid-sized public university. The participant’s institutional research responsibilities entail, among other things, conducting statistical analyses on important administrative metrics, such as retention, recruitment, and enrollment, and providing this information to their institution’s administration. Over four months, we conducted twelve semi-structured in-person and virtual interviews with the participant. Furthermore, during the interviews, the participant often shared data artifacts, such as an ongoing project on enrollment projections and trends, while discussing the practices associated with their everyday work. While studying one participant is a unique sample size, the STIR method has traditionally been used with small teams of scientific laboratory workers. Studying just one institutional researcher is adequate given the often solo nature of this type of professional’s work. Moreover, working with one individual allowed us to develop an intimate rapport and gain access to sensitive information shared by the participant, which may have been held back if we had also been working with her peers.

We developed an interview protocol to guide the participant to reflect on her privacy practices and those of her staff within the office of institutional research. The interviews sought to elicit from the participant reflections upon four decision components: the institutional research activities that they engage in (opportunities); the reasons for and against their practices (considerations); possible alternative approaches to their activities and reasons that might lead to acting on those alternatives (alternatives); and the possible outcomes if such outcome were acted upon (outcomes) (Reference Flipse, van der Sanden and OsseweijerFlipse, van der Sanden, and Osseweijer, 2013) to identify the rules-in-use, values, goals, and other socio-technical variables that shaped the practitioner’s privacy practice.

4.3.6 Data Analysis Procedures

We digitally recorded all interviews, using the audio to create transcriptions for coding purposes. We imported transcripts into MAXQDA, a qualitative data analysis application, and then coded interviews based on a two-stage approach. First, Reference Crawford and OstromCrawford and Ostrom’s (1995) institutional grammar approach was used to identify the rules-in-use that governed the practitioner’s institutional research privacy practices. These codes assessed the rules, norms, and strategies, and each of these rules-in-use’s associated attributes, aims, conditions, deontics, and consequences associated with the Governing Knowledge Commons (GKC) framework devised by Reference Sanfilippo, Frischmann and StrandburgSanfilippo, Frischmann, and Strandburg (2018). At the same time as these items were coded, we coded for the level at which a particular rule-in-use existed: individual, office, institution, external to the institution. Second, the interviews were then coded based on the STIR approach to identify the four socio-technical decision components, followed by codes for identifying the various socio-technical modulations that emerged throughout the interview process. What follows is relevant background information on institutional researchers and the findings we uncovered from our GKC-informed STIR.

4.4.1 Higher Education Intelligences

Institutional research is a branch of educational research that concentrates on improving “understanding, planning, and operating of institutions of postsecondary education” (Reference PetersonPeterson, 1999, 84). The role of institutional researchers is then to provide information to institutional administrators to aid in the improvement of planning, policy generation, and effective decision-making. Reference Volkwein, Liu, Woodell, Richard, MacLaughlin and KnightVolkwien, Liu, and Woodell (2012, 23) suggest that the institutional researcher is engaged in three areas of study, which they call the “golden triangle of institutional research”:

1. 1. institutional reporting and administrative policy analysis;

2. 2. strategic planning, enrollment, and financial management;

3. 3. outcomes assessment, program review, accountability, accreditation, and institutional effectiveness.

Furthermore, institutional researchers are called upon to not only provide information to facilitate improvement in these areas, but to actively engage in information sharing practices that contribute to organizational learning and, in turn, improve institutional effectiveness (Reference Borden, Kezar, Howard, McLaughlin and KnightBorden and Kezar, 2012).

Effective institutional research practices require that the institutional researcher engage three types of intelligences as they relate to their institution and higher education in general: technical and analytical; issues; and contextual and cultural (Reference TerenziniTerenzini, 1999). Given the diversity of these intelligences, institutional researchers have to balance various, and often competing, demands from administrators internal to their institutions, and from their external constituents, including state and federal policy makers, and their local communities (Reference VolkweinVolkwein, 1999). One such balancing concerns what Reference VolkweinVolkwien (1999, 13) calls, “enrollment pressures.” Institutions are “asked to simultaneously admit more students (for financial health and access) and become more selective (to bolster academic standards and performance measures).” For this reason, he likens the institutional researcher to Janus, the two-faced Roman God of “doors and gateways” in that they have to look inward toward internal improvement, while contemporaneously facing outward to ensure that they are attuned to external accountability demands.

4.4.2 Information and Knowledge Managers

In addition to appraising the demands of variegated internal and external actors, Reference SerbanSerban (2002) emphasizes the institutional researcher’s role regarding managing the flow of institutional data and information throughout their institutions. It is for this reason that the institutional researcher should also be understood as their institution’s knowledge manager, whereby they are responsible for the “processes that underlie the knowledge management framework – creation, capturing, and sharing of knowledge – that serve both internal and external purposes and audiences” (Reference SerbanSerban, 2002, 105). Understanding and addressing the complexity of the flow of institutional information and data throughout institutions of higher education is necessary given growing interest in advanced analytic practices.

Where once there was a time when institutional researchers served as their institution’s “one source of truth,” this new environment is leading to situations where “decision makers at all levels are establishing their own data collection processes and analytics” (Reference Swing and RossSwing and Ross, 2016, 5). Reference Zilvinskis, Willis and BordenZilvinskis, Willis, and Borden (2017, 12) argue that broad interest in analytics across campus units and offices creates a new situation where institutional researchers are playing a different role, writing: “[w]orking on learning analytics projects requires IR staff to engage with colleagues who tend to use information in operational and individualized contexts rather than the more strategic and aggregate uses to which they are accustomed.” This is so because institutional research offices are no longer the primary source of data, information, and analytic insights; each academic unit and office increasingly uses highly contextual data to serve their information needs. For instance, advisors are adopting analytic systems to analyze student movement through curricula, and information technology offices are developing their own metrics and data dashboards to evaluate system usage and services. Reference Swing and RossSwing and Ross (2016) contend that because data flows are becoming more complex and analytics more widespread, institutional researchers should become more actively engaged in managing and shaping of policies regarding the flow and use of institutional information and data.

4.4.3 Governing Sensitive Institutional Data and Information

Among professional institutional research associations and in the research literature, there have been ongoing conversations about principles, rules, and national and institutional policies that do or should govern uses of institutional information (Reference ShiltzShiltz, 1992). Much of this work concerns privacy as it relates to security, confidentiality, and appropriate use. And since student data and information is of chief importance in institutional research, policy conversations tend to revolve around students and less about faculty and staff.

On a national level, institutional research practices are bound by the Family Educational Rights and Privacy Act (FERPA). The law dictates that educational institutions who receive federal funding must protect and hold in confidence student data and information considered a part of a student’s identifiable educational record. Institutional actors have the right to gain access to such records when they have a legitimate educational interest in doing so. However, Reference FullerFuller (2017a) argues that institutional researchers are often unaware or undertrained regarding FERPA. According to a survey of 232 institutional researchers, 53 percent self-taught themselves about FERPA, while 22.5 percent had received no training. Lacking in knowledge of FERPA and its relation to data privacy matters should be a matter of concern, given that data breaches and other FERPA violations have led to numerous institutions being litigated in recent years (Reference FullerFuller, 2017b). Knowledge of and training with regard to FERPA is especially important given that the law’s definitions and requirements are imprecise and/or able to be bent based on an institution’s interpretations (Reference ZeideZeide, 2016).

Information sharing and information flow practices are also guided by professional ethics, institutional policies, and personal values (Reference FullerFuller, 2017b). Regarding professional ethics, the Association for Institutional Research (2013) outlines how institutional researchers should handle privacy issues in their Code of Ethics. However, the code is scant on this issue and merely states that institutional researchers should balance privacy risks and confidentiality against the potential benefits that the information can provide to the institution. Additionally, institutional researchers’ practices are supposed to be informed by internal institutional policies on data privacy. However, Reference FullerFuller (2017b) claims that many institutions do not have formal written policies.

4.4.4 Ethical Murkiness

The ambiguity in federal law, the “squishiness” of codes of ethics, and possibly the lack of guiding institutional information policy leads institutional researchers into a murky, ethical gray area. Researchers acknowledge that educational data analytics – a social and technological practice – raises significant ethical concerns (see Reference Slade and PrinslooSlade and Prinsloo, 2013). If data analytics produced by institutional researchers and others are to be considered trustworthy and legitimate, then they must attend to the ethical issues, the so-called “critical barriers” that will determine success and failure of data-based analytic initiatives (Reference Gašević, Dawson and JelenaGašević, Dawson, and Jovanović, 2016, 2). Higher education analytics are “moral practice[s]” (Reference Slade and PrinslooSlade and Prinsloo, 2013, 1519) that must account for actual and potential harms brought about data and information access, analysis, and use (Reference Pardo and SiemensPardo and Siemens, 2014).

4.5.1 Attributes

The findings below highlight how various information resources, policies, institutional actors, and various – and sometimes divergent – goals and objectives influence and frame the work done by the institutional researcher who participated in our socio-technical integration research (STIR). But briefly, it is important to highlight how these attributes make up the contextual background of the participant.

The participant’s resources are data-based and informational. She relied on datasets in various forms to complete her responsibilities, and she primarily used a centralized data warehouse to access and export data to her local computer for statistical analysis and data visualization purposes. Some but not all data sets were shared on a local network in the office of institutional research with specific user permissions set to limit access and protect sensitive data. Notably, the office’s information infrastructure was described differently in terms of its data security protections when compared to other offices on campus. The datasets were comprised of identifiable and de-identified student data, in addition to “raw” and aggregate data provided by other institutional offices, including among others human resources and admissions.

The participant’s office was, as expected, comprised of a staff of roughly twenty individuals. The makeup of the staff included administrators, data analysts, institutional researchers, and part-time graduate assistants. It would not be accurate to think that this office worked in a silo; they often collaborated with institutional administration to provide them actionable information and worked with other offices on campus when specific projects needed access to and analysis of institutional data. The work the institutional research office did was shaped and limited at times by the political interests of those to whom they reported data findings, as well as policy set by the institution’s office of information technology.

The goals and values of the institutional research and her office were not made explicit during interviews. However, such things were made clear upon examining the office’s documentation. The office strives to provide actionable information to support decision-making throughout the campus, as well as support the institution’s wider goals around student success and the effective operation of the campus. It is notable that the office explicitly aims to provide access to a data infrastructure and related tools, signaling that its staff wishes to be enablers of data – not gatekeepers – and help institutional colleagues leverage data in innovative ways.

4.5.2 Existing Rules-in-Use

The analysis of the conversations with the participant uncovered the rules-in-use (norms, rules, and strategies) that govern her work practices with institutional data. Furthermore, the analysis found that addressing the levels at which rules-in-use occur is important for understanding how rules-in-use emerge and differ in practice. For this analysis, we found rules-in-use at the following levels: individual, office, institution, and external-to-the-institution. The level of the rules-in-use impacted their scope and determined what and how they were governed. Understanding rules-in-use and the levels at which they occur will be important for our to-be-discussed STIR findings, where we explore the participant’s reflections upon and her modulations of her privacy practices and, in turn, the rules-in-use that govern her practice.

The participant’s privacy practices are governed by a variety of rules, most of which occur at the external-to-the-institution, institution, and office levels. Regarding the rules external to the institution, her and her colleagues are required to follow the appropriate FERPA guidelines. At the university level, university rules require that the participant and her colleagues are compliant with rules related to data sharing and use, such as ensuring that data consumers have the proper data use training and have signed the institution’s data use agreement in order to receive and share data. At the office level, the participant described rules primarily related to working with the university’s institutional review board (IRB) prior to conducting research and ensuring that she and her colleagues are up to date with institutional and federal privacy policies.

Regarding the norms, these predominantly occur at the institution and office levels. At the institution level, the norms revolve around data use for institutional improvement. According to the participant, the institutional norm is that data should be shared and made available to those seeking to improve the educational mission of the institution to develop useful insights. As the participant stated, “I think it’s been a policy [at the university] that we share information and we don’t try to silo things.” Given this, it is expected that her office collaborates with and supports other offices across the campus. The office level norms that guide the participant and her office’s practices relate primarily to protocols for how to share data with those external to their office and how student data should be de-identified in their institutional research products, such as in reports, dashboards, and data sets.

The strategies that govern the participant’s privacy practices primarily occur at the office and individual levels. These relate to spatial privacy practices and the appropriate use of student data. Spatial privacy practices refer to how the participant and her colleagues consider and modify their work and office spaces to ensure that student data are kept secure. Regarding office level strategies for appropriate data use, the participant stated that they assist data consumers to develop their business use cases when requesting access to institutional data. In addition, her office collaborates with other campus offices when they have questions about data access and use rules and norms.

Based on the analysis of the rules-in-use occurring at the office and individual levels an interesting trend emerged. The office and individual rules-in-use that the participant and her colleagues developed were in response to instances when the institution failed to adequately govern the participant’s privacy practices. In some instances, the office and individual’s rules-in-use explicitly contradicted that of the institution, but in other situations individual rules-in-use at the office and individual levels were developed in response to gaps at the institutional and federal levels. These contradictions and gaps will be further explained in the following section, where we discuss the findings of the STIR analysis.

4.5.3 Rethinking Rules-in-Use with Socio-Technical Integration Research

Conversations with the participant probed to examine the socio-technical conditions of her work regarding data practices and privacy. These probing questions enabled the participant to reflect on her workaday routines, but also to nudge the participant to examine the criteria (e.g., values, principles, procedures) that inform decisions a part of her routines. As we describe below, the participant was acutely knowledgeable of privacy issues, related processes and procedures, and had even developed unique privacy-protecting strategies.

The participant was keenly aware of the fact that data to which she had access, especially student data, were sensitive and needed to be kept secure. She expressed a personal ethos of responsibility, suggesting several times that data handling actions needed care and attention to potential downstream privacy effects. When asked why she felt this normative responsibility, she replied, “Why is it so important to protect student data in the way that we are? Because we’re here for the students because we want to make sure that we’re not creating any kind of violation, that we’re not violating this trust that they have.” Notably, she suggests that her ethos is one to which her institutional research peers subscribe as well. Additionally, the motivation for protecting the privacy of those she analyzes in data is due to a sense of obligation to uphold the trust data subjects have in her, but also the institution, to use data appropriately. If trust was something that could be violated, we asked, then what would be the consequences? To this probing question, she suggested that 1) students would not be willing participants in research projects and 2) her office would “lose access to some of the data that we need to be able to do our jobs” due to non-compliance with existing policies.

Before beginning her analytical work, the participant claimed that she strategically worked with her institution’s institutional review board (IRB), using it as a means to discuss and protect data privacy. “We tend to err on the side of caution,” she said, “and at least talk to IRB about every single project that we do … . We want to at the very least make IRB aware of [the project] and get some sort of approval.” Pursuing an “ethical consultation” with IRB, to the participant, would help her understand if her work was “consistent with good ethical research practices,” in compliance with federal rules, and in alignment with what the institution expects regarding access to student data. The IRB could help her limit downstream harms, such as the following she expressed in a conversation:

After working with the IRB, the participant described the process for gaining access to data. Institutional policy limited who within the institution could gain access to different sources of data. Depending on the source of the data, the participant would have to consult with a dedicated data steward (e.g., the registrar for enrollment data, the bursar for financial data, or a library administrator for library data). Conversations with the stewards required her to “build a business use case to justify” data access and use. The participant emphasized that the creation of the “business use case” was a collaborative process, and she stated that finding the necessary justification would not be as easy at other institutions where data sharing was more restrictive and there was less value placed on analytics based on combinable data from across various offices.

Before conversations gained significant traction, the participant would have to prove that she had successfully passed the institution’s FERPA training and consented to its data use agreement; both processes informed the participant of her legal and institutional responsibilities. Since her office also serves as a source of institutional data and information, the participant also asked for proof of the same compliance credentials from those with whom she worked within the institution. Notably, she questioned if others thoughtfully considered the compliance measures like she did, saying, “I would hope that everybody reads that information and takes it seriously; I don’t have any kind of assurance.” When she provides a data set, she makes the data requester “promise” that data will not be shared unless carefully outlined and approved ahead of time, detail how the data will be used, and share their data deletion strategies, all in order to make sure that institutional policy compliance is assured. When data requests proved difficult to determine access and use privileges, she consulted with other data stewards to seek their interpretations. The participant did not detail requirements that guided these types of conversations and blindly trusted that all data stewards would be just as rigorous in their analysis of data use requests.

About her office’s data privacy practices, she revealed a significant detail concerning the physical layout of her own office and that of her colleagues. The conversation unfolded in this way:

When her office hires student workers who do not have the benefit of a secure office, students are made aware of the fact that their work may involve sensitive data and that they should situate their computer screens to limit others from looking over their shoulders. The participant noted that her office’s privacy-protecting strategies were not as stringent as those in other offices, such as financial aid, whose employees “keep the windows drawn” and do not allow unaccompanied visitors.

Regarding digital data privacy practices, the participant expressed two strategies. First, another employee in the office was in charge of maintaining scoped data pulls from administrative systems (e.g., the student information system) and subsequently checking the veracity of the data. Having a point person for this data practice reduced inaccurate data and limited access to data unnecessary for informing analytic projects (i.e., they followed data minimization principles). Second, any analytics created by the office abided by their own rule that for data including a sample size of five or less, the reportable number changes to an asterisk. For instance, if a data dashboard includes aggregate data demonstrating that three Hawaiian/Pacific Islander students reflected a certain behavior or outcome, then the number would be masked to reduce reidentification risks. The participant emphasized that this rule went beyond less stringent requirements set by FERPA and guidance by the registrar’s office.

When the participant described her privacy practices – or a lack thereof in some cases – we prompted her to discuss alternative ways of thinking, doing, and valuing. The purpose of this strategy was to provide intellectual space and time to consider how outcomes of her privacy practices could be different and to reconsider the stimuli motivating standard practices. Responses to this strategy ranged from affirmative alternative designs (e.g., “I could do this … ”) to negative responses (e.g., “There is no other possibility … ”) due to existing conditions. The following highlights two instances where the participant outlined possible alternatives and outcomes.

An ongoing frustrating experience for the participant concerned her relationship with the institution’s office of information technology (OIT). Part of her position’s responsibility covered creating internal use and publicly available data dashboards, which required permission from an internal review panel and OIT. She expressed that even in cases where the internal review panel gives permission, OIT removes the dashboard – but they often fail to tell the participant that they had done so. Consequently, she “has to play ball” with OIT even if their decision would align with the internal review panel in the first place; if she does not, she loses her completed work.

The purpose for OIT rules is to protect data and the privacy of data subjects. But, the participant argued that these rules were too restrictive and unconstructive:

We confirmed with the participant that the issue boils down to a lack of trust between OIT and the office of institutional research, among others, and asked what she could do to get a different result. Even though she expressed skepticism that OIT would change its behavior and views, she noted that communications between her office could be more strategic. For instance, any issues with OIT decisions should be communicated from administrators from the office of institutional research, and not staffers. Additionally, attempts to “make nice” with OIT are preferable and probably more efficacious in the long run than battling OIT’s decisions. These alternatives were not optimal, but the participant perceived they could prove to be better than existing practices.

Another instance of alternative practices and outcomes concerned the development of new policy. The participant’s status as an administrator, not just an analyst, meant that she had policy-making privileges. If she desired and felt it would be useful, she could develop standardized data use practices with related compliance measures to guide her work and that of her peers within the office of institutional research. When the conversation shifted to this possibility, the response was negative. Her argument against forcing new policy was as follows (note: names changed to protect those referenced):

Considering the alternative enabled the participant to take stock of a potential outcome, which even though it was denied still proved useful. Thinking through the possibilities enabled her to consider the expertise of her peers (e.g., Jane and FERPA), knowledge of institutional policy and procedure (e.g., Danica as a data steward), location of various data and who knew of such data (e.g., Jonathan and HR data), and the norms and expectations around collaboration (e.g., as developed with Susan’s leadership).

4.5.4 Modulating Practice

With the participant made more aware of the socio-technical dimensions of her work due to the STIR conversations, she began to think through different strategies for navigating rules-in-use regarding her data practices and data privacy. Analysis of the findings suggest that the participant engaged in a greater number of reflexive deliberations than deliberate modulations. In what follows, we report on the participant’s most clearly articulated reflexive deliberation regarding foregrounding privacy and a series of deliberate, second-order modulations.

Towards the end of the interview sessions, the participant began to reflect on the topics covered, issues discussed, and useful takeaways. Not all of these contemplations led to weighty considerations, but one significant reflexive deliberation concerned a new approach to her thinking on privacy. When asked to consider what, if anything, had been influential about her time with the researchers, she answered in detail:

The simple statement of “being cognizant” reveals a heightened awareness in the participant’s mind about the important of privacy in her daily practices. It also demonstrates that she recognizes that privacy entails a variety of different rules-in-use, not just following institutional policy (though noted). This reflexive deliberation suggests that “being cognizant” takes focus and awareness, yet the common tasks and pressures – not to forget institutional politics – of the job intervene. To be cognizant involves pursuing strategies, such as vetting individuals requesting sensitive data and more carefully navigating information sharing expectations. Moreover, having privacy in the forefront of her mind, she believes, will enable her to think more carefully about the downstream consequences of sharing sensitive data. Finally, this deliberation also gave rise to a recognition that committing to ongoing professional education about her privacy responsibilities and the policies that govern her practices would better assist her in her work.

Based on the conversations with the participant, three types of deliberate modulations emerged: documentation of office data sharing and security practices; collaboration with data consumers on campus to help them use institutional data properly; and creation of a campus group to determine appropriate data sharing practices. Notably, these modulations reflect an “action arena” in the Governing Knowledge Commons (GKC) framework (Reference Sanfilippo, Frischmann and StrandburgSanfilippo, Frischmann, and Strandburg, 2018). These modulations will be addressed shortly, but it should be noted first that all of the participant’s modulations are considered second-order deliberate modulations, as opposed to first-order.

First-order modulations focus on actual changes in the STIR participant’s practices, whereas second-order are modulations where the participant alters her project’s goals, objectives, and assumptions to such a degree that they “come to challenge their own established routines of thought and practice, and also crucially, the various external forces which shape these” (Reference WynneWynne, 2011, p. 794). In the case of this study’s deliberate modulations, by the end of the study the participant had yet to make actual changes in their practices, rather they reflected upon the need for substantial changes in their future practices, and in some cases, set the stage for first-order modulations to occur.

The first second-order deliberate modulation that the participant reflected upon focuses on creating opportunities for her and her staff to document the implicit strategies and norms that guide their practices, such as spatial privacy practices and the norms that guide how they share data with campus data consumers. As the participant stated, documentation had not been an integral part of her office’s culture: “I think being a little bit more intentional about documenting policies for how we share data and things like that would probably be a good idea for our office and something that we haven’t really thought too much about.”

The participant reflected upon how the conversations led her to start a conversation with her supervisor about creating documentation opportunities, which could include setting aside dedicated office time during the week, such as “documentation Fridays,” focusing on documentation strategies as a team during a staff retreat or during office meetings, or by encouraging staff to document their practices concurrently as they work. The participant reflected that documenting office practices would help to reify and make explicit her office’s rules and norms, and to help justify their practices to others within the institution:

For the second of the second-order deliberate modulations, the participant reflected upon the need for her and her staff to actively work with data consumers on campus to inform them about proper institutional data use in ways that align with campus and federal-level rules and norms. As the findings suggest, the campus requires data consumers to adhere to rules in regards to having appropriate FERPA training and data use agreements signed. However, the participant stated the need for ensuring that the campus’ existing rules and norms are followed by working with data consumers to ensure that they understand proper data storage practices and protect institutional data they receive:

The final second-order deliberate modulation addresses the need for creating a campus-level initiative focused on developing standardized data sharing best practices. As addressed in the previous section, throughout the conversations the participant reflected upon the lack of campus-level rules and norms governing data sharing practices. Given this, the various offices on campus with data sharing responsibilities, including her own, have created their own rules and norms governing how data should be shared.

Historically, campus offices had limited interactions with one another regarding campus data sharing practices; data analysis had not been central to their respective work. But with it becoming so and the pressures increasing to make data-informed decisions, the participant recognized the need for developing consistent practices and policies across campus. “We’ve never really gotten together a group of people,” she said, “and just kind of discussed it out here, discussed things with the exception of like a handful of large-scale projects, um, that are about to be released.” There was a need, the participant expressed, for creating a campus group to discuss standardized data sharing practices on the campus, and that it was “not something that I had really thought to do before.” She and her supervisor were planning to meet to discuss how they might go about creating this campus group.

5.3.1 Day Without Immigrants

Participants, including members and followers, and non-member discussants within various DWI Facebook groups provided a rich depiction of the background context in which they were organizing, emphasizing how both supportive participants and their opposition saw the movement as fitting into a larger narrative of social and political dimensions, including recognition of how the movement related to the 2016 presidential election. Discussion, and embedded arguments, focused on what was perceived to have changed under President Trump; while many recognized the historical path, “The immigration system is broken and for most of the Central America and South America countries the only way to come here is a stupid lottery created 50 years ago,” others recognized the rhetorical changes in the national dialogue as leading to something different, for example contesting that “Donald Trump was talking about … CRIMINAL illegal immigrants.” Action was perceived to be required in order to fight against both the historical trend and the current threats. As one organizer explained, “Gracias. Injustice under Trump is not only seen more, but more severe. It is an important time to act and I need to be a part, for myself and for others.”

The DWI movement thus emerged from a background environment in which many supporters, as potential participants, had serious concerns about potentially dire consequences for themselves or their family members if they were identified in a public forum. President Trump’s anti-immigrant campaign rhetoric and promises heightened fears of discrimination and racial violence for many immigrants, especially Latinos, whether documented or undocumented, as well as fears of mass deportation for undocumented immigrants, including hundreds of thousands of DACA recipients and millions of DREAMERS (Reference KocherKocher, 2017).

One consequence of the heightened vulnerability of undocumented immigrants was that many of their documented friends and relatives felt a similarly heightened responsibility, despite their own fears of discrimination and retaliation, to take up visible roles in the movement, since such roles were perceived as too dangerous for the undocumented.

5.3.2 Women’s March

The Women’s March was galvanized by President Trump’s election in a contest that most expected Hillary Clinton, the nation’s first female presidential candidate, to win. Many women experienced Trump’s win over Clinton, despite her substantial expertise and government experience and his complete lack of either, as a wake-up call. Women’s outrage over Trump’s election was heightened by his record of disrespectful behavior and comments, including those recorded on the infamous Access Hollywood tape, and the numerous sexual harassment and assault allegations that emerged shortly before the election.

The background environment included the long-standing movement for women’s rights. Equality and respect, as both objectives and core values of the historic women’s movement, shaped Women’s March institutions in fundamental ways. Specific values emphasized centered on inclusion and privacy, as concerns about safety, in the wake of sexual harassment and assault allegations against President Trump and recent history of #gamergate, made concerns about targeting individuals serious (Reference Moss and MaddrellMoss and Madrell, 2017).

5.3.3 March for Science

Unlike the other two movements, the March for Science did not grow out of a historical political movement responding to discrimination or hostility. Rather, it was a response to a fear that science was in danger of losing the nearly universal status and acceptance that it has enjoyed in modern times. An anti-science strain had been emerging in US politics for a few years, particularly within the Republican Party, particularly in relation to issues such as energy and climate change (Reference SelepakSelepak, 2018). The 2016 campaign, culminating in President Trump’s election, crystallized and heightened scientists’ fears that facts, objectivity, and scientific evidence were being supplanted in public discourse and decision-making by reliance on experience, personalization of information in favor of beliefs over facts, and conspiracy theories. These threats to scientific values were accompanied by more practical concerns about the possibilities of funding cuts, disruption of accepted scientific standards for peer review and allocation of funding, and corruption of the output of government-supported scientific endeavors.

Reflecting its emergence out of concerns for loss of historical status, the March for Science drew from the outset directly on the support and resources of large and established scientific professional organizations. In this respect, it differed notably from both the Women’s March and DWI. In deciding whether to become involved in the political arena by organizing a March for Science, scientific organizations and individual participants confronted the question of whether participating, as scientists, in a movement that responded directly to the election of a particular president would violate scientific norms of objectivity that had ordinarily been understood to include political nonpartisanship. Some members of the scientific community viewed participation as a means of opposing an already dangerous politicization of science, while others feared that employing the tools of political advocacy on behalf of science would contribute to its further politicization.

5.4.1 Community Members

5.4.2 Resources

Across all three movements, information resources were developed, aggregated, and shared to inform members, other participants, impacted individuals, and the general public about the movements’ objectives and events, as well as to share human interest stories and news coverage of their activities, and provide information resources for impacted populations. By using public Facebook pages, groups from all three movements made these shared information resources open resources, leveraging the visibility Facebook, and other social media platforms, provided to cultivate their own knowledge resources for use by affected individuals beyond participating stakeholders.

Prioritization of choice and opportunity shaped not only each group’s online information sharing practices, as described with respect to the mailing lists and organizational partnerships, but also the information resources constructed (Reference KitchKitch, 2018). Facebook and social media were most visibly central to the Women’s March, perhaps partly because of the role social media played in the group’s origins, but also because social media were seen as legitimate forums for personal information and sharing by participants in this movement. Facebook was not, however, considered to be perfect for this or any movement. Other tools and channels, such as EventBrite, were deemed necessary both to allow organizers to better anticipate numbers of demonstrators and to ensure that feminists and supporters who did not participate in Facebook could be adequately up to date on important information.

Facebook also had a significant impact on these activist movements because of the way it affected dialogue, by increasing disinhibition and opening groups to criticism, rather than simply insulating them. Interestingly, the smaller the group, the less it appears to attract critical posts, even when a small satellite was organized in a place where one would expect little ideological alignment between the movement and the populace at large. This was especially the case for small DWI groups, but also seemed to be true for smaller Women’s March satellites. Furthermore, some groups defused opposition by describing their membership in more socially acceptable terms; for example, groups organized by students and “DREAMERS” were perceived to be “sort of good that kids care about STEM” and “the kind of immigrants we want” (Facebook posts). “Asian and well-educated” immigration groups were also complimented, even by individuals who publicly stated their opposition to the DWI movement overall. In contrast, plenty of opposition was expressed relative to “Mexican, undocumented” groups. Obvious stereotypes played out in this environment, particularly relative to the perceived legitimacy of action arenas and resources, as individuals were open about their fears and prejudices in the mediated environment. In the words of one Facebook post, “Like you would even say that if this wasn’t fb!”

In the course of their activities, these groups handled large amounts of personal information. Some of this information was in the obvious form of contact information for members of the Facebook groups and those who RSVP’d using their real identities on EventBrite. But other personal information emerged less obviously, from discussions in the Facebook groups as individuals debated issues and told personal stories, or in photos taken at demonstrations. All of these forms of personal information were absolutely central resources for these movements, enabling coordination, publicity, public engagement, and more for these groups.

5.4.3 Goals and Objectives

The objectives underlying the movements are tied strongly to the exogenous influences associated with their formation, as well as to historical interests shaping their contexts. These objectives reflect common values such as equality, transparency, truth, and fairness, as well as interests unique to each group. The general goal of each of these three movements, though details are specific to each movement and group, is, in part, to resist Trump’s agenda in favor of more progressive policies and changes. All groups also shared the objective of informing the public about their focal issues. Groups uniformly placed high value on knowledge production and, as described in the previous section, on maintaining the veracity and quality of the group’s information resources.

All of the movements were confronted by entrenched political opposition. Sometimes there were subareas within a movement’s objectives where consensus with at least some opposition actors could be reached. For example, children of immigrants were viewed relatively favorably and DACA was a more acceptable issue to address than amnesty. As one Facebook user stated “Yes the people who have crossed the border without a choice are the children they bring, are they criminals too?” Supporters and many who originally identified as the opposition agreed that children had no choice and thus this was seen to be a legitimate objective.

Sometimes, however, opposition led to counter-movements, or even harassment and threats. While some Women’s Marches saw anti-abortion, or more specifically, anti-Planned Parenthood, counter-protesters, DWI groups experienced the most visible detractors, with bigoted and hateful language directed toward them, as well as threats made toward exposing individuals to scrutiny over their own statuses. Even the well-sourced resources and campaigns developed by the March for Science was subjected to the same hostility to objectivity that the movement emerged to address. When intelligent public information campaigns were disseminated, comments were posted decrying them as propaganda; for example “Drinking the left wing koolaid made by the C.linton N.ews N.etwork.”

The national March for Science group developed and disseminated a relatively clear set of top-down objectives, while the Women’s March and DWI movements presented patchworks of objectives even at the national level. Regardless of the degree of consistency at the national level, satellite groups unavoidably augmented and modified national objectives to reflect local contexts.

Many March for Science satellite groups were defined more specifically by goals and objectives determined in the local context. For example, the backgrounds of the individuals determining the agenda and specifying the goals varied from group to group. For example, one group might be organized by the American Association for the Advancement of Science (AAAS) members, while another was organized by high school science teachers. Differences between groups within the March for Science movement could be sufficiently stark to provoke some prospective participants to eschew the closest group in favor of a geographically inconvenient alternative. For example, an organizer for the March for Science Austin reported:

This interviewee joined and helped to organize a satellite group located hours away because of dissatisfaction with the fact that the local satellite group was focused too much on public health and improving trust in biomedical resources, rather than encompassing broader issues such as climate change or general esteem for science.

The Women’s March had a strong national presence, but many individual satellite groups were very well organized and developed their own values and goals very independently, with only the loosest of coordination with the national group. DWI groups were the most grassroots in nature, yet shared information, practices, and institutions horizontally to great effect, illustrating the strength of the network in developing something to a large scale, despite the fact that some satellite demonstrations did not even occur on the same date as the national event. For example, while most demonstrations took place on February 16, 2017, Milwaukee had its demonstrations three days prior. Organizers of individual satellite marches and walk-outs emphasized the importance of solidarity in objectives, as much as in actions, throughout interviews. One organizer explained group-to-group interaction, as a process of assimilation that did not involve any top-down pressure or aggregation, but rather depended on coordinated interactions between many individuals:

Satellite groups often wanted to learn from one another and leverage national numbers to attract attention to their causes, while serving their own specific communities.

Tensions and dissension about goals and objectives sometimes led satellite groups to differentiate themselves from the national group. Even provocations by outsiders might lead to productive discussions about how the scope of a group’s objectives could be narrowed in a way that was acceptable to at least some detractors. For example, a post stating “Immigrants are great! But illegal aliens should not be here. I wish the two wouldn’t be used to mean the same thing” triggered a discussion that led one local movement to focus on demands for immigration reform, consideration for families, and respectful dialogue, rather than including calls for amnesty. This approach made that satellite group a relative outlier within the larger movement.

Even the language used to frame problems and objectives was sometimes contested. For example, posts in various DWI Facebook groups related to whether the objectives, and underlying problems, were about illegal or undocumented individuals, “aliens” or “criminals.” Extreme objectors posted things like:

In response to these debates, very different agreements and discussions evolved within different local groups across the country as outside stakeholders contested the legitimacy of the groups and groups responded.

Other provocations re-shaped demonstrations. For example:

In response to this post, this group designed a more inclusive demonstration, with friends and supporters obfuscating the status of their undocumented classmates.

5.5.1 Institutions

Polycentric institutional arrangements defined governance within these cases. Within legal and regulatory institutions regarding freedoms of association and expression, Facebook and other platforms, including EventBrite, Twitter, Slack, and Snapchat provide overarching infrastructure in which individual groups created their own institutions, which alternately abide, work around, or contradict the constraints placed upon them within the nested structure.

Governance mechanisms within these movements were distinctive, yet membership rules, resource contribution, and knowledge sharing expectations had many similarities. For example, very broadly, the membership norm was to have low barriers to entry, without expectations to contribute information or actively organize. Yet there was a clear norm that attendees should publicize and share event details and information resources that were generated by the more active participants.

Across all three movements, there was little explicit discussion of rules within Facebook groups or on other public platforms. Nonetheless, normative expectations about civility in dialogue were often specified (e.g. “yes, i’m sorry it is a little condescending, please edit that out if you could or i’ll delete it when i get back :) your heart is in the right place but no human is superior than another human”). Norms of authority were reflected in requests to provide references or sources in order to back up claims (e.g. “I didn’t see that. Where did you read that? I’m not saying it isn’t true, but”) or assist other members (e.g. “can you share those details”) were ubiquitous.

The logic, as well as the process, of decision-making in these groups was often non-transparent, despite the groups’ ostensibly open nature. For groups at the national level, as well as satellites in large cities such as NYC or Seattle, the lack of transparency sometimes stemmed from the fact that such large groups became dysfunctional when too many people were involved in organizing and decision-making. For smaller satellites, lack of transparency often emerged simply because one or two individuals alone acted as the driving forces of these groups. Furthermore, because much of the decision-making process in these groups occurred off of the public Facebook groups, the best sense of how governance was handled comes from the Facebook group FAQs and from interviews. Moderation of discussion in the Facebook groups was an apparent form of governance. And, of course, governance is also formalized in the technological infrastructure and configurations of platforms.

Informal norms and strategies, relative to how people interacted and what was acceptable information to share, were emerged in an ad hoc fashion and by example, rather than from thoughtful strategic planning. Thus, there were many levels of institutionalization and few internal objections to governance designs for these groups. Overall, responses to our survey suggest that the governance was perceived to be legitimate, though there was sometimes disagreement about particular choices.

Privacy, as governance of personal information flow, was often not discussed publicly, even when privacy was a primary focus of many FAQs, discussions amongst organizers, and provided the logic behind numerous decisions. It is notable that interviewees cited their movements’ privacy values very confidently, even when they had not discussed them explicitly with others in the group; “I’m not sure … I … as we have talked, this idea has come to me, but it’s not something we decided on … I think we are informal and local, loose connections to other immigrant groups, because it provides privacy and keeps people safe.”

Some specific rules-in-use about personal information were discussed prominently, however, including those against oversharing in light of threats associated with disclosure outside of the group (e.g. “Everybody: Don’t share immigration statuses. Privacy settings don’t hide comments. It’s a public group”). Questions about appropriateness were common in the Facebook postings, for example “should we really post pictures? there is no expectation of privacy at a public event” (Facebook post). Beyond privacy-related rules-in-use reflected in the posted discussions, heavy moderation was easily evident on the public Facebook pages of some groups. For example, of 4,352 posts associated with the seven DWI groups that we studied, only 3,946 still have readable text, indicating that 406 have been deleted. Timestamp and post ID, without a post, are downloadable metadata through the API, and in some cases it is possible to infer what the post may have discussed, by looking at responses that are still visible on the page. This illustrates both a privacy threat and an instance in which polycentric governance is competitive, rather than complimentary. While many of the deletions by organizers moderating these pages were intended to remove inappropriate flows of personal information that had been shared, as enforcement of rules governing DWI groups, overarching platform level governance by Facebook undermined this effort, to an extent, by maintaining context and metadata.

There were very real concerns expressed by movement members about surveillance and about what Facebook would do with the data it had amassed about individual participants and groups overall. While this concern was most prominently expressed in relation to DWI groups, members of groups across all three movements echoed the concern. As one organizer explained:

Many individuals, across all three movements, expressed doubts about the legitimacy of Facebook’s role in making decisions about their groups’ information. Furthermore, there was entrenched distrust that Facebook would adhere to what was stated in policies; “We agree to Facebook when we use it, but they don’t always do what they say and it changes” (March for Science participant, survey response). Nonetheless, most felt it was necessary to sacrifice in order to benefit from Facebook’s social capabilities. They did not see any alternative.

While rules and expectations about conduct within groups were often implicit, aside from rules about sharing information and admonitions to mind norms about civil conversations, there was active enforcement of content and civility standards through moderation. These practices were frustrating to some good-faith participants, who did not understand the implicit expectations, yet faced explicit consequences in moderation. Moderation more often manifested when group organizers simply deleted posts that didn’t reflect community standards but, occasionally, organizers would articulate expectations and give participants an opportunity to edit their posts, with deletion serving as a last resort. Beyond censorship, there were no other real consequences or sanctions for violations and conflicts between members or members and outsiders were resolved on an ad hoc basis or through excision by moderators, rather than through any formal or consistent procedure.

5.5.2 Actors in Governance

Actors involved in governance, regardless of movement or satellite group, were not always key stakeholder groups and did not include all members in any case. Yet interactions between groups and the permeability of boundaries were often relatively open, allowing for interested and committed individuals to be as involved as they wanted to. DWI groups were relatively the most different than other groups, in terms of having most key organizing roles filled by advocates and family members, rather than undocumented individuals themselves, as least in terms of how these groups documented and presented themselves to outsiders in order to protect impacted individuals’ privacy. As one DWI organizer, for a student-led satellite group, explained:

The organizers, in some cases relatives of immigrants, were themselves simply “civically engaged” and wanted to ensure that their families and classmates were welcome in the community. Other DWI groups were organized by DREAMERS, as well as friends and relatives, and made decisions independent of, yet representing, the impacted communities. In contrast, most Women’s Marches were organized by women.

March for Science decision-makers often included a combination of scientists, science educators, and STEM students, along with other STEM advocates. As one March for Science organizer explained:

This movement was in many cases more collaborative.

Actors involved in governance often expressed their desire to be inclusive, yet also their fears of being influenced by those with contrary values, particularly given concurrent activism by “white supremacists and Neo-Nazis.” Boundaries were open, but actively policed, in order to avoid co-option. It was also particularly interesting to see who the groups, or the interacting public, attempted to exclude, given that they were working within open, public Facebook groups. Stakeholder groups wanted to engage the public, but not necessarily everyone in their own networks. As one organizer of a DWI satellite group responded, when asked about establishing boundaries:

In this sense, members within groups often leveraged their control, as enabled by Facebook, over who specific posts would be shared with, based on whether they were friends and family, or colleagues, driven by concerns about repercussions from nested oversight.

Decision-makers in all groups were often those who felt personally invested and frustrated with current politics, becoming involved through social media and interpersonal interactions and relationships. Actors who engaged in organizing in most cases were in small, close knit groups, yet at the national level and in some of the largest satellites, large groups coordinated. Smaller satellites were often organized by 1 to 25 individuals, in contrast to the roughly 1000-member group that organized the national Women’s March. Overall, decision-makers were generally perceived to be legitimate in organizing, though criticism remained about the non-representative nature of many of the Women’s March groups, in particular.

5.7.1 Privacy Values in Public Facebook Groups

Despite the obvious impact of privacy values and practices on political demonstrations and movements, the most innovative applications of privacy as governance within these communities shaped the use of public Facebook groups, often in ways specific to ideological or sensitive uses of this technology. Four distinct privacy values emerge, shaping public Facebook groups as commons arrangements: privacy through obscurity; privacy and chilling effects; privacy through autonomy; and participatory privacy.

Privacy was, in many instances, sought through obscurity. Various groups and individuals emphasized the anonymity provided to them by the crowds in demonstrations and the relative safety they felt within the sheer number of supporters, often beyond the expectations of organizers and the media in advance of events. Governance structures around photographs and publicity particularly emphasized this preference, minimizing the ability to single out participants publicly, to the best of their abilities. Large groups also emphasized privacy through obscurity in their configurations of Facebook groups and common patterns of engagement, allowing public numbers, without identities, within RSVP design and through the use of “following” rather than “joining” mechanisms.

Privacy concerns also generated chilling effects, regarding participation patterns. This was closely coupled to fear of repercussions, rather than inappropriate flows alone, with many informants for this research conflating these two problems. Comparing immigration advocacy groups to the Women’s March, there were differences in not documenting or “lurking” participation for the immigrants’ groups, in comparison to subtle behavioral shifts, or deleting documentation, for the women’s groups. While merely symptoms of the more primary surveillance harms and possible repercussions, they represent distinct burdens and tradeoffs surrounding participation (Brennan-Marquez & Susser, work in progress). In this sense, privacy dramatically shaped participation, in addition to resources and governance.

Participatory privacy – including anonymous and pseudonymous participation, as well as non-identifiable participation in a crowd – presented a related set of strategies yet was independent of chilling effects and drew on diversity of modes of interaction. Specifically, the use of multiple platforms and institutional designs that obfuscated identification of sensitive attributes associated with stakeholders in the communities provided a means of participatory privacy, whether though encrypted channels for organization of immigration groups or proxy participants, as well as the use of existing organizational infrastructure, by March for Science groups, to protect junior scientists’ careers. Central to Facebook specifically, choices made by individual participants to utilize the least publicly transparent modes of interaction with public groups illustrate nuance to participatory privacy. Following, rather than joining, a group allowed individuals to include information from the groups in their newsfeeds and notifications, without anyone else knowing they were followers. Similarly, liking a group without joining it supported sharing the interest only with friends, rather than with the general public.

Privacy was also attained by many through autonomy. A commons arrangement, in which individuals and collectives had control over flows, rather than accepting other decision-makers’ choices around appropriateness or imposed flows, provided acceptable outcomes regarding personal information. Groups made choices to use multiple channels and delete contact resources, in order to contradict default practices or designs of platforms and prevent privacy harms imposed by platforms, law enforcement, or political opposition. These creative choices and work-arounds reflected a desire to overcome the structural and institutional efforts by online platforms, like Facebook, to undermine social norms about appropriate information flows (e.g. Reference StrandburgStrandburg, 2004, Reference Strandburg2006) and were relatively successful at providing privacy to participants and stakeholders.

5.7.2 Commons Governance for Grassroots Political Organizing

The GKC provided a useful lens through which to explore how grassroots political organizing in public online spaces functions through commons governance, including privacy as governance. Not only were numerous norms and strategies revealed, as evidence of dependence on lower levels of institutionalization in complex and diverse contexts, but also the polycentric nature of governance arrangements was made visible.

Specifically, not only did individual movements have unique needs, which generated arrangement patterns, but individual groups illustrated creative ways of interacting with platforms like Facebook in their efforts to appropriately structure their communities. Differences in choices about platforms, as well as what arrangements of tools and configurations within those platforms, illustrated experimentation and context specificity, as well as distinct limitations of Facebook. While Facebook allows groups to control events, those created by individuals cannot be shared with other accounts, from an administrative standpoint, leading to inconveniences, as well as lack of functionality, for example, depending on the scope and development patterns for each group. Another example of a flaw for organizing related to what groups had access to, which varied by scope; larger groups did not have access to full lists of respondents to verify against EventBrite RSVPs, though Facebook has access to who might attend. Furthermore, many unique arrangements were designed to protect privacy, through the use of less public channels.

5.7.3 Emerging Best Practices

While the scale and frame of this study do not lend themselves toward best generalizable principles for online organizing, a number of privacy practices can be identified from these groups as emerging best practices, reflecting a grounded approach toward description, rather than prescription. Specific privacy institutions are shared within and across movements, with respect to how to handle personally identifiable stories, contact information, event photographs, and discussion moderation.

First, and most broadly accepted, it appears to be a key to success to use multiple platforms, particularly for predicting turnout through RSVP functions and in generating and protecting email lists or other contact information. This allows groups to reach more diverse communities with shared interests, as well as to triangulate. While groups had different expectations around what to do with those forms of information, it was considered best practice to have multiple platforms and not entrust everything to a single platform.

Second, photographs should be archived off of public platforms, regardless of whether they are deemed appropriate to also be hosted on commercial public platforms. Private servers, rather than cloud services, were more often trusted, though some did depend on secure cloud back up. Many groups also backed up contact lists, though there was not a clear consensus on how to do this, and notable exceptions actually deleted all of this information, as well.

Third, in organizing around contentious political issues within public online spaces, moderation has been deemed absolutely critical, even if the extent of moderation and the underlying rationales are different. While some groups were concerned about removing hate speech or fake information, others were concerned about detraction from their carefully constructed messages; whatever the reason, some control over the content is important in pursuing specific goals and maintain civil spaces.

Fourth, efforts were made in diverse groups to protect the personal stories and prevent identifiability of vulnerable members. Even though scientists perceived as public intellectuals were encouraged to disclose personal stories, junior scientists were protected in ways that were similar to individuals’ immigration statuses and women in vulnerable situations, often associated with sexual harassment or domestic violence.