Big Data and Social Science: Data Science Methods and Tools for Research and Practice, Second Edition shows how to apply data science to real-world problems, covering all stages of a data-intensive social science or policy project. Prominent leaders in the social sciences, statistics, and computer science as well as the field of data science provide a unique perspective on how to apply modern social science research principles and current analytical and computational tools. The text teaches you how to identify and collect appropriate data, apply data science methods and tools to the data, and recognize and respond to data errors, biases, and limitations.
- Takes an accessible, hands-on approach to handling new types of data in the social sciences
- Presents the key data science tools in a non-intimidating way to both social and data scientists while keeping the focus on research questions and purposes
- Illustrates social science and data science principles through real-world problems
- Links computer science concepts to practical social science research
- Promotes good scientific practice
- Provides freely available workbooks with data, code, and practical programming exercises, through Binder and GitHub
New to the Second Edition:
- Increased use of examples from different areas of social sciences
- New chapter on dealing with Bias and Fairness in Machine Learning models
- Expanded chapters focusing on Machine Learning and Text Analysis
- Revamped hands-on Jupyter notebooks to reinforce concepts covered in each chapter
This classroom-tested book fills a major gap in graduate- and professional-level data science and social science education. It can be used to train a new generation of social data scientists to tackle real-world problems and improve the skills and competencies of applied social scientists and public policy practitioners. It empowers you to use the massive and rapidly growing amounts of available data to interpret economic and social activities in a scientific and rigorous manner.
Table of Contents
2. Working with Web Data and APIs - Cameron Neylon
3. Record Linkage - Joshua Tokle and Stefan Bender
4. Databases - Ian Foster and Pascal Heus
5. Scaling up through Parallel and Distributed Computing - Huy Vo and Claudio Silva
6. Information Visualization - M. Adil Yalcin and Catherine Plaisant
7. Machine Learning - Rayid Ghani and Malte Schierholz
8. Text Analysis - Evgeny Klochikhin and Jordan Boyd-Graber
9. Networks: The Basics - Jason Owen-Smith
10. Data Quality and Inference Errors - Paul P. Biemer
11. Bias and Fairness - Kit T. Rodolfa, Pedro Saleiro, and Rayid Ghani
12. Privacy and Confidentiality - Stefan Bender, Ron Jarmin, Frauke Kreuter, and Julia Lane
13. Workbooks - Brian Kim, Christoph Kern, Jonathan Scott Morgan, Clayton Hunter, and Avishek Kumar
Ian Foster, PhD, is a professor of computer science at the University of Chicago as well as a senior scientist and distinguished fellow at Argonne National Laboratory. His research addresses innovative applications of distributed, parallel, and data-intensive computing technologies to scientific problems in such domains as climate change and biomedicine. Methods and software developed under his leadership underpin many large national and international cyberinfrastructures. He is a fellow of the American Association for the Advancement of Science, the Association for Computing Machinery, and the British Computer Society. He earned a PhD in computer science from Imperial College London.
Rayid Ghani is a professor in the Machine Learning Department (in the School of Computer Science) and the Heinz College of Information Systems and Public Policy at Carnegie Mellon University. His research focuses on developing and using Machine Learning, AI, and Data Science methods for solving high impact social good and public policy problems in a fair and equitable way across criminal justice, education, healthcare, energy, transportation, economic development, workforce development and public safety. He is also the founder and director of the “Data Science for Social Good” summer program for aspiring data scientists to work on data mining, machine learning, big data, and data science projects with social impact. Previously Rayid Ghani was a faculty member at University of Chicago, and prior to that, served as the Chief Scientist for Obama for America (Obama 2012 Campaign).
Ron Jarmin, PhD, is the Deputy Director at the U.S. Census Bureau. He earned a PhD in economics from the University of Oregon and has published in the areas of industrial organization, business dynamics, entrepreneurship, technology and firm performance, urban economics, Big Data, data access and statistical disclosure avoidance. He oversees the Census Bureau’s large portfolio of data collection, research and dissemination activities for critical economic and social statistics including the 2020 Decennial Census of Population and Housing.
Frauke Kreuter, PhD, is Professor at the University of Maryland in the Joint Program in Survey Methodology, Professor of Statistics and Methodology at the University of Mannheim and head of the Statistical Methods group at the Institute for Employment Research in Nuremberg, Germany. She is founder of the International Program in Survey and Data Science, co-founder of the Coleridge Initiative, fellow of the American Statistical Association (ASA), and recipient of the WSS Cox and the ASA Links Lecture Awards. Her research focuses on data quality, privacy, and the effects of bias in data collection on statistical estimates and algorithmic fairness.
Julia Lane, PhD, is a professor at the NYU Wagner Graduate School of Public Service. She is also an NYU Provostial Fellow for Innovation Analytics. She co-founded the Coleridge Initiative as well as UMETRICS and STAR METRICS programs at the National Science Foundation, established a data enclave at NORC/University of Chicago, and co-founded the Longitudinal Employer-Household Dynamics Program at the U.S. Census Bureau and the Linked Employer Employee Database at Statistics New Zealand. She is the author/editor of 10 books and the author of more than 70 articles in leading journals, including Nature and Science. She is an elected fellow of the American Association for the Advancement of Science and a fellow of the American Statistical Association.
"Like the first edition, the new edition will continue to play an important role for the intended audience and a wider professional community. The much-needed second edition is timely and showcases a wide range of examples and application examples from different areas of the social sciences to demonstrate how the methods are implemented using several real datasets. As expected with this kind of book, the topics of this text are diverse in nature, but interesting none the less. As it is well known, machine learning techniques are subject to inherited bias in model selection and consequently negatively impacts post estimation and prediction. This new edition includes a new chapter on dealing with bias and fairness in machine learning models, a much-needed fair and welcome edition! Further, the authors have done an excellent job in expanding the material on machine learning and text analysis. Like the first edition, the main strength of the book is that it offers a wide variety of applications that are based on real datasets emerging from social science perspectives and useful for both academic and professional communes. As Jupyter has become more popular as the data scientists’ computational notebook of choice, the book has new and improved hands-on Jupyter notebooks to complement each chapter’s material. In conclusion, this new edition has an impressive collection of material on useful and interesting topics on big data. The book will be equally useful to graduate students and researchers interested in gaining perspectives and knowledge on this important topic. The new volume comprises of a wealth of information, a kind of one-stop shop, and can be served as a textbook and research reference book."
- S. Ejaz Ahmed, Brock University, Canada
Praise For First Edition
"This book builds a nice bridge connecting social science and big data methodology. Big data such as social media and electronic health records, empowered by the advances in information technology, are an emerging phenomenon in recent years and present unprecedented opportunities for social science research. This book was written by pioneering scientists in applying big data methods to address social science problems. As shown by numerous examples in the book, social science could benefit significantly by embracing the new mode of big data and taking advantage of the technical progress in analysing such data. If you work in social science and would like to explore the power of big data, this book is clearly for you. Indeed, if you do not have previous experience in dealing with big data, you should read this book first, before implementing a big-data project.
As indicated by the title, this book acts as a practical guide and targets readers with minimum big data experience, hence it is very hands-on. … It covers all necessary steps to finish a big data project: collecting raw data, cleaning and preprocessing data, applying various modelling tools to analyze the data, evaluating results, protecting privacy, and addressing ethical problems. … All the important topics concerning big data are covered, making this book a good reference that you should always keep on your desk."
— Guoqiang Yu, Virginia Tech, in Journal of the American Statistical Association, July 2017
"…In summary, although there is a growing number of books related to social science and big data, this volume contains several non-trivial aspects which make it worth to have in the library, possibly along with other similar textbooks as a good complement to them."
—Stefano M. Iacus, University of Milan, in Journal of Statistical Software, June 2017
"This is a well-written book and showcases a good number of examples and applications to demonstrate how the methods are actually used in real life situation using real datasets. Further, topics at hand are motivated by social science data. … The chapters are nicely structured, well presented and motivated by data examples. The main strength of the book is that it still offers a good number of applications that are based on real datasets emerging from social science perspectives. The book will be useful to students, practitioners, and data analyst in the respective fields. The editors did a very good job introducing the book, it aims and goals, intendent audience, clarifying underneath concepts and phrases, a must read before moving to other chapters."
—S. Ejaz Ahmed, in Technometrics, April 2017
"Economists and Social Scientist have a lot to learn from Machine Learning, and Engineers have a lot to learn from Econometricians and Statisticians. This two way sharing is long overdue and it is time to start the conversation. This book is a tour-de-force for anyone interested in participating in such a discussion."
—Roberto Rigobon, Society of Sloan Fellows Professor of Applied Economics, MIT
"This ambitious sweep through data science techniques provides an invaluable introduction to the toolbox of big data methodologies, as applied to social science data. It provides tremendous value not only to beginners in the field, but also to experienced data scientists wishing round out their knowledge of this broad and dynamic field."
—Kenneth Benoit, Department of Methodology, London School of Economics and Political Science
"Most social scientists would agree that ‘big data’ – the term we use to encapsulate the huge amount of electronic information we generate in our everyday lives – provide the potential for path-breaking research not just into our economic, social, and political lives but also the physical environment we create and inhabit. However, few have the knowledge, or critically, the tools that equip them to realize this potential. This book provides a bridge between computer science, statistics, and the social sciences, demonstrating this new field of ‘data science’ via practical applications. The book is remarkable in many ways. It originates from classes taught by leading practitioners in this area to federal agency research staff, drawing in particular upon the example of a hugely successful project that linked federal research spending to outcomes in terms of patents, job creation, and the subsequent career development of researchers. By making these workbooks accessible, the book takes the novice on a step-by-step journey through complex areas such as database dynamics, data linkage, text analysis, networks and data visualization. The book is a treasure trove of information. It leads the field in the important task of bringing together computer science, statistics, and social science. I strongly recommend that all social scientists with an interest in ‘big data’ immerse themselves in this book."
—Professor Peter Elias CBE, University of Warwick
"The explosive growth in big data and in new technologies to analyze these data is transforming the practice of research in a variety of fields. Foster, et al. provides a well-timed, valuable guide to the new methods and tools associated with big data that can be used to address critical research questions in the social science field. The breadth of the material is impressive, providing a comprehensive summary of the methods and tools as well as practical guidance for their use. A key feature of the guide is the use of a case study to illustrate how big data techniques can be used to address a research question from beginning to end of the project, including providing examples of computer code targeted to specific steps in the project. Any researcher will find this unique guide to be useful, and it is essential reading for any social science practitioner that wants to use the best available data to conduct influential research in the near future."
—Paul Decker, President and CEO, Mathematica Policy Research
"The typical statistics pedagogy has changed. In the past, textbooks assumed that data was hard to obtain, but neatly organized in a single file. Today, data is very easy to obtain from a number of data sources, often very messy, and analysts are now responsible for organizing it in addition to deriving useful insights. Foster, Ghani, Jarmin, Kreuter, and Lane have assembled a book that gives a pointed overview of tools to facilitate the entire digital lifespan of data in this era of analytics. Big Data and Social Science gives an evenhanded look at the myriad of ways to obtain data--whether scraping the web, web APIs, or databases--to conducting statistical analysis to doing analysis when your data cannot fit on a single computer. Meanwhile, they provide sound, diligent advice on pitfalls that still, and will always, exist. A book like this is useful for social scientists, experienced statisticians, econometricians, and computer programmers who want to see the tools available to them. It will also be a helpful text for a budding data scientist who wants a fairly technical preview of the landscape."
—Tom Schenk Jr., Chief Data Officer, City of Chicago
"In Big Data and Social Science, the authors have deftly crafted one of the very best "how-to" books on big data that researchers, enterprise analysts, and government practitioners will find equally valuable. From Nodes, to Edges, to Arcs, the book takes the reader along a near-perfect path to understanding the fundamental elements of constructing a practical and realistic model for Big Data Analysis that any organization can execute by simply following the path outlined in this book. Elegant in its simplicity, Big Data and Social Science is one of those books that every research group and data-analysis team will want to have on their reference shelf."
—Tom Herzog, Former Deputy Commissioner, NY State Department of Corrections and Community Supervision