Proceedings of the International AAAI Conference on Web and Social Media · 2021 · 85 citations · 13 references
Social SciencesPolitical CommunicationPolitical ScienceData MiningPolitical BehaviorSocial Media AnalyticsClassificationParty IdentificationPolitical Communication AnalyticsSocial MediaSocial Media PoliticsTrend DetectionAutomated Text ClassificationElection Communication AnalysisPolitical Participation On Social MediaPolitical Party IdentificationSocial Media Political CommunicationTraining
Nowadays, the use of social media such as Twitter is necessary to monitor trends of people on political issues. As a case study, we collected the main stream of Twitter related to the 2010 UK general election during the associated period. We analyse the characteristics of the three main parties in the election. Also, we propose a simple and practical algorithm to identify the political leaning of users using the amount of Twitter messages which seem related to political parties. The experimental results showed that the best-performing classification method -- which uses the number of Twitter messages referring to a particular political party -- achieved about 86% classification accuracy without any training phase.
13
Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment
Andranik Tumasjan, Timm O. Sprenger, Philipp Sandner et al. · Proceedings of the International AAAI Conference on Web and Social Media · 2010 · 2.7K citations · Full text
Social Sciences, Political Communication, Political Science +12
From Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series
Brendan O’Connor, Ramnath Balasubramanyan, Bryan Routledge et al. · Proceedings of the International AAAI Conference on Web and Social Media · 2010 · 2K citations · Full text
Public Affairs, Political Communication, Political Science +17
Characterizing user behavior in online social networks
Fabrício Benevenuto, Tiago Rodrigues, Meeyoung Cha et al. · 2009 · 803 citations