Paper: Predicting the 2011 Dutch Senate Election Results with Twitter

ACL ID W12-0607
Title Predicting the 2011 Dutch Senate Election Results with Twitter
Venue Workshop on Semantic Analysis in Social Media
Session  
Year 2012
Authors

To what extend can one use Twitter in opin- ion polls for political elections? Merely counting Twitter messages mentioning po- litical party names is no guarantee for ob- taining good election predictions. By im- proving the quality of the document col- lection and by performing sentiment anal- ysis, predictions based on entity counts in tweets can be considerably improved, and become nearly as good as traditionally ob- tained opinion polls.

@InProceedings{tjongkimsang-bos:2012:SASM2012,
  author    = {Tjong Kim Sang, Erik  and  Bos, Johan},
  title     = {Predicting the 2011 Dutch Senate Election Results with Twitter},
  booktitle = {Proceedings of the Workshop on Semantic Analysis in Social Media},
  month     = {April},
  year      = {2012},
  address   = {Avignon, France},
  publisher = {Association for Computational Linguistics},
  pages     = {53--60},
  url       = {http://www.aclweb.org/anthology/W12-0607}
}