Text as Data: A New Framework for Machine Learning and the Social Sciences. Justin Grimmer, Margaret E. Roberts, and Brandon M. Stewart

Abstract

In the past decade, text-as-data methods have rapidly gained popularity among social scientists and researchers in the digital humanities, business, and government alike. It is becoming increasingly feasible to mine valuable information from documents as a consequence of abundant data, novel techniques, and declining computational costs. However, this plethora of new statistical models and computational tools have to be adapted if they are to address issues in the social sciences. Text as Data: A New Framework for Machine Learning and the Social Sciences is a guide to using tools for text as data to make predictions about present and future human behavior. It aims to inform social science research, offer guidance for scholars in the digital humanities, provide practical solutions to problems in industry, and ultimately address governance issues. Besides making substantial contributions to the social sciences, this book also has important implications for the advancement of the digital humanities.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 1 citations exist upstream.