Vox Populi

Jan. 1, 2015

In the Vox Populi project we try to monitor the opinion of the people by scanning social media (primarily Twitter). We are interested in political views and especially in predicting the outcome of elections on the basis of tweets. A preliminary study showed that by just counting tweets in which political parties are mentioned, we can approximate the polls. Because the posters on Twitter are not necessarily a cross-section of the population, we will research a number of filters to adjust this possible discrepancy. The filters we will be looking into are about: Clustering and topic detection (what are posts about?), User profiling (who is posting?), Sentiment analysis (what is the sentiment of messages?), External event detection (are there specific events that influence the people’s posts?), Time windowing (should we put relative weights on counts of tweets near a certain event (election)?)

Publications

The following publications regarding this project have been published:

E. Sanders, M. de Gier, and A. van den Bosch
Using Demographics in Predicting Election Results with Twitter
Proceedings of International Conference on Social Informatics. Springer International Publishing, 2016, 259-268, 2016
Full text (pdf), RIS, BibTex