A guide for using computational text analysis to learn about the social world From social media posts and text messages to digital government documents and archives, researchers are bombarded with a deluge of text reflecting the social world. This textual data gives unprecedented insights into fundamental questions in the social sciences, humanities, and industry. Meanwhile new machine learning tools are rapidly transforming the way science and business are conducted. Text as Data shows how to combine new sources of data, machine learning tools, and social science research design to develop and evaluate new insights. Text as Data is organized around the core tasks in research projects using text-representation, discovery, measurement, prediction, and causal inference. The authors offer a sequential, iterative, and inductive approach to research design. Each research task is presented complete with real-world applications, example methods, and a distinct style of task-focused research. Bridging many divides-computer science and social science, the qualitative and the quantitative, and industry and academia-Text as Data is an ideal resource for anyone wanting to analyze large collections of text in an era when data is abundant and computation is cheap, but the enduring challenges of social science remain. Overview of how to use text as data Research design for a world of data deluge Examples from across the social sciences and industry

This book demonstrates the consequences of legislators' strategic communication for representation in American politics. Representational Style in Congress shows how legislators present their work to cultivate constituent support. Using a massive new data set of texts from legislators and new statistical techniques to analyze the texts, this book provides comprehensive measures of what legislators say to constituents and explains why legislators adopt these styles. Using the new measures, Justin Grimmer shows how legislators affect how constituents evaluate their representatives and the consequences of strategic statements for political discourse. The introduction of new statistical techniques for political texts allows a more comprehensive and systematic analysis of what legislators say and why it matters than was previously possible. Using these new techniques, the book makes the compelling case that to understand political representation, we must understand what legislators say to constituents.

Constituents often fail to hold their representatives accountable for federal spending decisions--even though those very choices have a pervasive influence on American life. Why does this happen? Breaking new ground in the study of representation, "The Impression of Influence" demonstrates how legislators skillfully inform constituents with strategic communication and how this facilitates or undermines accountability. Using a massive collection of Congressional texts and innovative experiments and methods, the book shows how legislators create an impression of influence through credit-claiming messages.

Anticipating constituents' reactions, legislators claim credit for programs that elicit a positive response, making constituents believe their legislator is effectively representing their district. This spurs legislators to create and defend projects popular with their constituents. Yet legislators claim credit for much more--they announce projects long before they begin, deceptively imply they deserve credit for expenditures they had little role in securing, and boast about minuscule projects. Unfortunately, legislators get away with seeking credit broadly because constituents evaluate the actions that are reported, rather than the size of the expenditures.

"The Impression of Influence" raises critical questions about how citizens hold their political representatives accountable and when deception is allowable in a democracy.

A guide for using computational text analysis to learn about the social world From social media posts and text messages to digital government documents and archives, researchers are bombarded with a deluge of text reflecting the social world. This textual data gives unprecedented insights into fundamental questions in the social sciences, humanities, and industry. Meanwhile new machine learning tools are rapidly transforming the way science and business are conducted. Text as Data shows how to combine new sources of data, machine learning tools, and social science research design to develop and evaluate new insights. Text as Data is organized around the core tasks in research projects using text-representation, discovery, measurement, prediction, and causal inference. The authors offer a sequential, iterative, and inductive approach to research design. Each research task is presented complete with real-world applications, example methods, and a distinct style of task-focused research. Bridging many divides-computer science and social science, the qualitative and the quantitative, and industry and academia-Text as Data is an ideal resource for anyone wanting to analyze large collections of text in an era when data is abundant and computation is cheap, but the enduring challenges of social science remain. Overview of how to use text as data Research design for a world of data deluge Examples from across the social sciences and industry

Constituents often fail to hold their representatives accountable for federal spending decisions--even though those very choices have a pervasive influence on American life. Why does this happen? Breaking new ground in the study of representation, "The Impression of Influence" demonstrates how legislators skillfully inform constituents with strategic communication and how this facilitates or undermines accountability. Using a massive collection of Congressional texts and innovative experiments and methods, the book shows how legislators create an impression of influence through credit-claiming messages.

Anticipating constituents' reactions, legislators claim credit for programs that elicit a positive response, making constituents believe their legislator is effectively representing their district. This spurs legislators to create and defend projects popular with their constituents. Yet legislators claim credit for much more--they announce projects long before they begin, deceptively imply they deserve credit for expenditures they had little role in securing, and boast about minuscule projects. Unfortunately, legislators get away with seeking credit broadly because constituents evaluate the actions that are reported, rather than the size of the expenditures.

"The Impression of Influence" raises critical questions about how citizens hold their political representatives accountable and when deception is allowable in a democracy.