Using Twitter to Predict the Stock Market: Where is the Mood Effect?

Abstract

Behavioral finance researchers have shown that the stock market can be driven by emotions of market participants. In a number of recent studies mood levels have been extracted from Social Media applications in order to predict stock returns. We try to replicate these findings by measuring the mood states on Twitter. Our sample consists of roughly 100 million tweets that have been published in Germany between January, 2011 and November, 2013. In our first analysis we do not find a significant relationship between aggregate Twitter mood states and the stock market. However, in further analyses we also consider mood contagion by integrating the number of Twitter followers into the analysis. Our results show that it is necessary to consider the spread of mood states among Internet users. Based on our results in the training period, we created a trading strategy for the German stock market. Our portfolio increases by up to 36 percent within a six-month period after the consideration of transaction costs.

Nofer, Michael / Hinz, Oliver (2014). Using Twitter to Predict the Stock Market: Where is the Mood Effect? Business & Information Systems Engineering, forthcoming.