Twitter as a Tool for Predicting Elections Results

Abstract

The use of social networking sites, such as Twitter, for various purposes, continues to grown since its first appearance. This social net is a microblogging site to share short messages on a variety of topics. In particular, political elections are a very interesting field to exchange views using this platform. In this paper we have used Spanish elections to investigate the use of Twitter for this purpose, and to find out if the conversations maintained there can anticipate, in some way, the results of the elections. In order to do this, we have developed a tool, called Tara tweet, to define experiments and to capture the defined conversations, and have applied it to the cases of three Spanish elections during 2011 and 2012. Our results show that Twitter is used for political discussion, and that the references to the different political parties correlate, significatively, with the votes of the electors. This is an indicator that Twitter may be used by social researchers as a tool, among others, to predict future results of the elections. Of course, with due caution because the measured data correspond to distinct actions, so obviously, much more research and studies should be done in this field.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 66 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.