Predicting Voting Behavior Using Digital Trace Data. (October 2021)

• Record Type: Journal Article
• Authors: Bach, Ruben L.; Kern, Christoph; Amaya, Ashley; Keusch, Florian; Kreuter, Frauke; Hecht, Jan; Heinemann, Jonathan
• Other Names: Bosnjak Michael guest-editor.
• Is Part Of: Social science computer review. Volume 39:Number 5(2021)
• Page Start: 862
• Page End: 883
• Publication Date: 2021-10
• Subjects: web tracking -- voting -- digital traces; Social sciences -- Data processing -- Periodicals; Computers -- Social aspects -- Periodicals; Microcomputers -- Periodicals; Sciences sociales -- Informatique -- Périodiques; Micro-ordinateurs -- Périodiques; 300.285
• DOI: 10.1177/0894439319882896
• Languages: English
• ISSNs: 0894-4393

Abstract

A major concern arising from ubiquitous tracking of individuals' online activity is that algorithms may be trained to predict personal sensitive information, even for users who do not wish to reveal such information. Although previous research has shown that digital trace data can accurately predict sociodemographic characteristics, little is known about the potentials of such data to predict sensitive outcomes. Against this background, we investigate in this article whether we can accurately predict voting behavior, which is considered personal sensitive information in Germany and subject to strict privacy regulations. Using records of web browsing and mobile device usage of about 2, 000 online users eligible to vote in the 2017 German federal election combined with survey data from the same individuals, we find that online activities do not predict (self-reported) voting well in this population. These findings add to the debate about users' limited control over (inaccurate) personal information flows.