Friends With Text as Data Benefits: Assessing and Extending the Use of Automated Text Analysis in Political Science and Political Psychology

Date created: | Last Updated:


Creating DOI. Please wait...

Create DOI

Category: Project

Description: Applications of automated text analysis measuring topics, ideology, sentiment or even personality are booming in political science. These developments are to be applauded as they bring about novel insights about politics using new sources of (unstructured) data. However, a divide exists between researchers using text to study political competition on the one hand and those interested in political psychology on the other. In this paper we argue that both approaches will benefit from more integration, structuring our case around a number of core issues: (i) construct bycatch when searching text for ideology; (ii) preprocessing steps and the (disappearing) data of theoretical interest; (iii) the importance of knowing who delivered the text; and (iv) what text to use. Along the way we demonstrate that constructs like ideological placement, the use of sentiment words, and stop words use are strongly correlated and that analysts are easy to mistake on for another. As such, this paper aims to contribute to a critical discussion about the merits of automated text analysis methods in political science.

License: CC0 1.0 Universal

This project represents a preprint. Learn more about how to work with preprint files. View preprint


Loading files...



Recent Activity

Loading logs...

This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.

Create an Account Learn More Hide this message