Social media is an invaluable source of time-critical information during a crisis. However, emergency response and humanitarian relief organizations that would like to use this information struggle with an avalanche of social media messages – often exceeding human capacity to process.

Emergency managers, decision makers, and affected communities can make sense of social media through a combination of machine computation and human compassion. Machine computation takes many forms, including natural language processing, semantic technologies, data mining, machine learning, network analysis, human-computer interaction, and information visualization. Human compassion is expressed by thousands of digital volunteers who publish, process, and summarize potentially life-saving information.

This book brings together computational methods from many disciplines, focusing on methods that are commonly used for processing social media messages under time-critical constraints, and offering over 500 references to in-depth information.

Researchers and computer science students can read this book as an extended survey of methods to be improved, extended, or built upon through research. It can also be used in an integrative, applied course or seminar on mining the real-time Web.

Developers and practitioners can read this book as an overview of composable state-of-the-art methods that can be used to architect solutions for handling time-critical social media data. The discussion uses examples from current social media platforms, which of course may merge, become abandoned, or disappear in the future, but every effort has been made to make the discussion platform-agnostic.

Emergency relief and humanitarian response are fascinating topics that should attract some of the best minds in the scientific and technical communities. This book is an invitation for computer scientists and technologists who want to apply their skills to help disaster-affected communities by providing information, a basic need during disaster response.