"Is all that talk just noise? Predicting the future through social media"
We have recently started a project to explore the information content of microblogs and study in how far microblogging platforms such as Twitter can be used as an indicator of events in the offline world. In the context of the German federal elections, we have already shown that the information content of Twitter messages can serve to predict election results and reflect the political landscape quite well. The current focus is on the exploration of Twitter as an indicator of financial market activity. Other research areas include the use of microblogging as a channel for corporate communication and the reflection of brand sentiment on Twitter. Methodologically, we are using dictionary-based approaches and machine learning tools to classify message board content automatically and extract the sentiment contained in the postings.
Follow us on Twitter:
Stay tuned to our research and "all things TUitter": @TUitterResearch
Research papers
Working papers
Sprenger, T. & Welpe, I. (2011). Followers and foes: Industry classification based on investor perceptions of strategic peer groups (February 26, 2011). [Link to SSRN working paper version]
Sprenger, T. & Welpe, I. (2011). News or noise? The stock market reaction to different types of company-specific news events (January 4, 2011). [Link to SSRN working paper version]
Sprenger, T. & Welpe, I. (2010). Tweets and trades: The information content of stock microblogs (November 1, 2010). [Link to SSRN working paper version]
Articles in peer-reviewed journals
Tumasjan, A., Sprenger, T., Sandner, P., & Welpe, I. M. (forthcoming). "Where there is a sea there are pirates": Response to Jungherr, Jürgens, and Schoen. Social Science Computer Review (forthcoming).
Tumasjan, A., Sprenger, T. Sandner, P., & Welpe, I. (2010). Election forecasts with Twitter: How 140 characters reflect the political landscape. Social Science Computer Review. Advance online publication. doi: 10.1177/0894439310386557 [Link to SSRN working paper version]
Sprenger, T., Bolster, P. & Venkateswaran, A. (2007). Conditional Prediction Markets as Corporate Decision Support Systems – an Experimental Comparison with Group Deliberation. Journal of Prediction Markets, 1(3), 189-208.
Articles in refereed proceedings
Sprenger, T. (2011). TweetTrader.net: Leveraging crowd wisdom in a stock microblogging forum. Proceedings of the 5th International Conference of Weblogs and Social Media, Barcelona, Spain (forthcoming).
Feller, A., Kuhnert M., Sprenger, T. & Welpe, I. (2011). Divided They Tweet: The network structure of political microbloggers and discussion topics. Proceedings of the 5th International Conference of Weblogs and Social Media, Barcelona, Spain (forthcoming).
Tumasjan, A., Sprenger, T. Sandner, P. & Welpe, I. (2010). Predicting elections with Twitter: What 140 characters reveal about political sentiment. Proceedings of the 4th International Conference of Weblogs and Social Media, Washington, D.C. [Link to video of the conference presentation]
Student papers
Heilmann, C. (2010) Twitter as a Communication Channel for Executives and Virtual Team Leaders.