Download this Paper Open PDF in Browser

Election Forecasts with Twitter - How 140 Characters Reflect the Political Landscape

Social Science Computer Review, Vol. 29, pp. 402-418

37 Pages Posted: 10 May 2011 Last revised: 19 Aug 2014

Andranik Tumasjan

Technische Universität München - TUM School of Management

Timm O. Sprenger

Technische Universität München (TUM) - School of Management

Philipp G. Sandner

Frankfurt School of Finance & Management

Isabell M. Welpe

Technische Universität München (TUM) - School of Management

Date Written: January 1, 2011

Abstract

This study investigates whether microblogging messages on Twitter validly mirror the political landscape offline and can be used to predict election results. In the context of the 2009 German federal election, we conducted a sentiment analysis of over 100,000 messages containing a reference to either a political party or a politician. Our results show that Twitter is used extensively for political deliberation and that the mere number of party mentions accurately reflects the election result. The tweets' sentiment (e.g., positive and negative emotions associated with a politician) corresponds closely to voters' political preferences. In addition, party sentiment profiles reflect the similarity of political positions between parties. We derive suggestions for further research and discuss the use of microblogging services to aggregate dispersed information.

Keywords: Twitter, microblogging, information market, prediction markets, election forecasts, politics, elections, sentiment analysis

Suggested Citation

Tumasjan, Andranik and Sprenger, Timm O. and Sandner, Philipp G. and Welpe, Isabell M., Election Forecasts with Twitter - How 140 Characters Reflect the Political Landscape (January 1, 2011). Social Science Computer Review, Vol. 29, pp. 402-418. Available at SSRN: https://ssrn.com/abstract=1833192 or http://dx.doi.org/10.2139/ssrn.1833192

Andranik Tumasjan (Contact Author)

Technische Universität München - TUM School of Management ( email )

Leopoldstr. 139
Munich, D-80804
Germany

HOME PAGE: http://www.strategie.wi.tum.de/index.php?id=20

Timm O. Sprenger

Technische Universität München (TUM) - School of Management ( email )

Arcisstrasse 21
Munich, 80333
Germany
+49-(0)89-289-24800 (Phone)
+49-(0)89-289-24805 (Fax)

HOME PAGE: http://www.strategie.wi.tum.de

Philipp Sandner

Frankfurt School of Finance & Management ( email )

Sonnemannstraße 9-11
Frankfurt am Main, 60314
Germany

HOME PAGE: http://www.philipp-sandner.de

Isabell M. Welpe

Technische Universität München (TUM) - School of Management ( email )

Leopoldstrasse 139
Munich, 80804
Germany
++49/89/289-24800 (Phone)
++49/89/289-24805 (Fax)

HOME PAGE: http://www.strategie.wi.tum.de

Paper statistics

Downloads
432
Rank
55,047
Abstract Views
1,975