An Analysis of the Twitter Discussion on the 2016 Austrian Presidential Elections

In this paper, we provide a systematic analysis of the Twitter discussion on the 2016 Austrian presidential elections. In particular, we extracted and analyzed a data-set consisting of 343645 Twitter messages related to the 2016 Austrian presidential elections. Our analysis combines methods from network science, sentiment analysis, as well as bot detection. Among other things, we found that: a) the winner of the election (Alexander Van der Bellen) was considerably more popular and influential on Twitter than his opponent, b) the Twitter followers of Van der Bellen substantially participated in the spread of misinformation about him, c) there was a clear polarization in terms of the sentiments spread by Twitter followers of the two presidential candidates, d) the in-degree and out-degree distributions of the underlying communication network are heavy-tailed, and e) compared to other recent events, such as the 2016 Brexit referendum or the 2016 US presidential elections, only a very small number of bots participated in the Twitter discussion on the 2016 Austrian presidential election.