Researchers to Crowds to Algorithms: Building Large, Complex, and Transparent Databases from Text in the Age of Data Science
July 6, 2014
This article reviews available text analysis approaches and their limited success generating rich, transparent databases at scale. After elucidating the precise difficulties faced by previous projects and methods, the article introduces a new approach to text analysis featuring innovative procedures and open source tools to optimally combine the efforts of researchers, crowds, and algorithms. The article describes the first substantive project deploying the approach, imagines other projects on theoretical/empirical frontiers enabled by the approach, and closes with promising implications for social science when researchers are able to generate larger, more complex, transparent databases faster.
Number of Pages in PDF File: 94
Keywords: text analysis, crowdsourcing, machine learning, event analysis, crowd work, content analysis, algorithmsworking papers series
Date posted: June 27, 2014 ; Last revised: November 28, 2014
© 2015 Social Science Electronic Publishing, Inc. All Rights Reserved.
This page was processed by apollo5 in 0.531 seconds