Big Crisis Data - front cover

Big Crisis Data

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 that exceeds human capacity to process.

This book brings together computational methods from many disciplines: natural language processing, semantic technologies, data mining, machine learning, network analysis, human-computer interaction, and information visualization, focusing on methods that are commonly used for processing social media messages under time-critical constraints, and offering more than 500 references to in-depth information.

Cambridge University Press / July 2016 / 224 pages.

Book contents

Read the table of contents (pdf)

Part I: computer processing

The first part (Chapters 2-6) focuses on the technical aspects of data processing, and follows computing disciplines of databases, natural language processing, machine learning, network analysis, and online algorithms.

Part II: human factors

The second part (Chapters 8-11) focuses aspects from information sciences and human factors, including crowdsourcing, human-computer interaction, computer-supported collaborative work, and information visualization.

Real-world examples

Describes actual systems operating during real crises.

Extensive bibliography

More than 500 references to in-depth information.

Reviews

«Castillo has provided an accessible path through a wide and sometimes unwieldy literature on crisis informatics. This book has an important and timely focus on big data issues, which both challenge and enlighten our understanding of human behavior in disaster events.»

Leysia Palen, Professor of Computer Science, and Professor and Founding Chair of the Department of Information Science, University of Colorado, Boulder.

«Gaining situational awareness in a disaster is critical and time sensitive in nature. Social media presents the possibilities of a new and exciting data source to help improve response in the early hours and days of a crisis. Castillo has not only researched, but also contributed to building technologies that help both to make sense of social media and to integrate it into existing information flows and decision-making processes. This book helps walk the reader through the state of the art in several aspects of the big crisis data field, including many elements that are important for these technologies to have real-world impact.»

Andrej Verity, Co-Founder of the Digital Humanitarian Network, and Information Management Officer at the United Nations Office for the Coordination of Humanitarian Affairs.

«Social media has played an indispensable role during all of the recent disasters and crises. If you are a researcher looking for ways to make sense of the data that inundates us during such events or a practitioner struggling to make such data actionable, this book needs to be your first source. Castillo has masterfully synthesized a large number of techniques and capabilities in a unified framework to cover this already broad field for the reader.»

Amit Sheth, Executive Director of Kno.e.sis, Wright State University, Ohio.

Read a sample

Read the first 10 pages (pdf)

Other options:

Follow on Facebook and Twitter for future announcements.

Sample pages

Purchase the book now!

Cambridge University Press, July 2016. 224 pages. Hardcover and e-book editions available.

If you buy from Cambridge, enter promo code CASTILLO on check-out for a 20% discount (valid through Dec. 2016).

Resources: Data, Software, and Tools

For pointers to data and tools, see the book's wiki page at the Humanitarian Computing Library.

  • Software for natural language processing and machine learning.
  • Datasets of crisis-related social media messages.
  • Data repositories of humanitarian and emergency response information.
  • Videos of talks and seminars on social media during crises by various researchers.
  • Related conferences, workshops, and journals

Humanitarian Computing Library