Can social media reveal the preferences of voters? A comparison between sentiment analysis and traditional opinion polls. Issue 1 (2nd January 2017)

• Record Type: Journal Article
• Authors: Oliveira, Daniel José Silva; Bermejo, Paulo Henrique de Souza; dos Santos, Pâmela Aparecida
• Is Part Of: Journal of information technology & politics. Volume 14:Issue 1(2017)
• Page Start: 34
• Page End: 45
• Publication Date: 2017-01-02
• Subjects: Elections -- opinion mining -- opinion polls -- sentiment analysis -- social media -- Twitter; Electronic government information -- Periodicals; Internet in public administration -- Periodicals; Information technology -- Political aspects -- Periodicals; 320.0285
• DOI: 10.1080/19331681.2016.1214094
• Languages: English
• ISSNs: 1933-1681

Abstract

ABSTRACT: This study aims to determine whether the results obtained by applying sentiment analysis to data extracted from social media can reveal the political preferences of citizens to a greater degree of accuracy than traditional public opinion surveys. The researcher collected and analyzed 92, 441 tweets related to the Brazilian presidential candidates during the second round of elections in 2014. The analysis results were compared with six voter preference polls conducted by the Datafolha Research Institute. The results showed that sentiment analysis may indicate voter preferences at an accuracy that was only 1% to 8% different than that of traditional research, which has an average accuracy of 81.05%.