2015/05/06 by Pete Burnap, Rachel Gibson, Burnap, Pete +7 · 2 citations
Social Sciences · #Computers and Society (cs.CY) #Electoral Systems and Political Participation #FOS: Computer and information sciences #FOS: Physical sciences #Physics and Society (physics.soc-ph) #Social Media and Politics #Social and Cultural Dynamics #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1505.01511
openalex publication_date 2015/05/06 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
The election forecasting 'industry' is a growing one, both in the volume of\nscholars producing forecasts and methodological diversity. In recent years a\nnew approach has emerged that relies on social media and particularly Twitter\ndata to predict election outcomes. While some studies have shown the method to\nhold a surprising degree of accuracy there has been criticism over the lack of\nconsistency and clarity in the methods used, along with inevitable problems of\npopulation bias. In this paper we set out a 'baseline' model for using Twitter\nas an election forecasting tool that we then apply to the UK 2015 General\nElection. The paper builds on existing literature by extending the use of\nTwitter as a forecasting tool to the UK context and identifying its\nlimitations, particularly with regard to its application in a multi-party\nenvironment with geographic concentration of power for minor parties.\n