Predição do resultado das eleições presidenciais do Brasil baseado em tuítes
Resumo
Este trabalho utiliza o contexto das eleições presidenciais do Brasil no ano de 2014 para investigar se o vencedor de uma eleição pode ser descoberto a partir de mensagens públicas dos usuários do Twitter. Aproximadamente 3 milhões e 200 mil mensagens, de mais de 460.000 mil usuários distintos, fazendo referência aos principais presidenciáveis foram coletadas e analisadas. Nossos resultados mostram que é possível estimar o resultado das eleições baseado apenas na técnica de contagem de tuítes. Outros resultados obtidos mostram também que outras técnicas como contagem de usuários e análise de sentimentos de mensagens podem aumentar a acurácia dos modelos de predição.
Palavras-chave:
Predição do Resultado, Eleições Presidenciais, Twitter
Referências
Bakker, T. P. (2011). Good news for the future? Young people, Internet use, and political participation. Communication Research.
Beauchamp, N. (2013). Predicting and interpolating state-level polling using twitter textual data. Meeting on automated text analysis, London School of Economics.
Cameron, M. P. (2013). Can Social Media Predict Election Results? Evidence from New Zealand. No. 13/08.
Ceron, A. C. (2014). Using Sentiment Analysis to Monitor Electoral Campaigns: Method Matters—Evidence From the United States and Italy. Social Science Computer Review.
Choy, M. C. (2011). A sentiment analysis of Singapore Presidential Election 2011 using Twitter data with census correction. arXiv preprint arXiv:1108.5520.
Choy, M. C. (2012). US Presidential Election 2012 Prediction using Census Corrected Twitter Model. arXiv preprint arXiv:1211.0938.
Chung, J. E. (2011). Can collective sentiment expressed on twitter predict political elections? AAAI.
Eleições 2014. Pesquisa eleitoral para presidente. Disponível em: http://www.eleicoes2014.com.br/pesquisa-eleitoral-para-presidente/. Acesso em: 10 abr. 2014.
Fink, C. B. (2013). Twitter, Public Opinion, and the 2011 Nigerian Presidential Election. 2013 International Conference on Social Computing (SocialCom). IEEE., 311-320.
Fumagalli, L. &. (2011). The total survey error paradigm and pre-election polls: The case of the 2006 Italian general elections. ISER Working Paper Series. 2011-29.
Gaurav, M. S. (2013). Leveraging candidate popularity on Twitter to predict election outcome. Proceedings of the 7th Workshop on Social Network Mining and Analysis. ACM., 7.
Gayo Avello, D. (2011). Don't turn social media into another'Literary Digest'poll. Communications of the ACM, 54(10), 121-128.
Hillygus, D. S. (2011). The evolution of election polling in the United States. Public opinion quarterly, 75(5),, 962-981.
Jungherr, A. J. (2012). Why the pirate party won the german election of 2009 or the trouble with predictions: A response to tumasjan, a., sprenger, to, sander, pg, & welpe, im “predicting elections with twitter: What 140 characters reveal about political sentiment”. Social Science Computer Review, 30(2),, 229-234.
Lewis-Beck, M. S. (2005). Election forecasting: principles and practice. The British Journal of Politics & International Relations, 7(2),, 145-164.
Makazhanov, A. R. (2014). Predicting political preference of Twitter users. Social Network Analysis and Mining, 1-15.
Mejova, Y. S. (2013). GOP primary season on twitter: popular political sentiment in social media. Proceedings of the sixth ACM international conference on Web search and data mining, 517-526.
Mislove, A. L. (2011). Understanding the Demographics of Twitter Users. ICWSM, 11, 5th.
Nooralahzadeh, F. A. (2013). 2012 Presidential Elections on Twitter--An Analysis of How the US and French Election were Reflected in Tweets. Control Systems and Computer Science (CSCS), 2013 19th International Conference on, 240-246.
O'Connor, B. B. (2010). From tweets to polls: Linking text sentiment to public opinion time series. ICWSM, 11, 122-129.
Paula Filho, W.; GARCIA, A. C. B. RoTuEl: A Semi-Automated Method For Labeling Political. In: Doctoral Consortium at International Joint Conference on Artificial Intelligence (IJCAI-15), 2015, Buenos Aires, Argentina. Proceedings of the Twenty-Four IJCAI.
Prasetyo, N. D. (2014). Tweet-Based Election Prediction (Doctoral dissertation, TU Delft, Delft University of Technology).
Sang, E. T. (2012). Predicting the 2011 dutch senate election results with twitter. the Workshop on Semantic Analysis in Social Media (pp. 53-60). Association for Computational Linguistics.
Tumasjan, A. S. (2010). Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment. ICWSM, 10, 178-185.
Wong, F. T. (2013). Media, pundits and the us presidential election: Quantifying political leanings from tweets. In Proceedings of the International Conference on Weblogs and Social Media.
Beauchamp, N. (2013). Predicting and interpolating state-level polling using twitter textual data. Meeting on automated text analysis, London School of Economics.
Cameron, M. P. (2013). Can Social Media Predict Election Results? Evidence from New Zealand. No. 13/08.
Ceron, A. C. (2014). Using Sentiment Analysis to Monitor Electoral Campaigns: Method Matters—Evidence From the United States and Italy. Social Science Computer Review.
Choy, M. C. (2011). A sentiment analysis of Singapore Presidential Election 2011 using Twitter data with census correction. arXiv preprint arXiv:1108.5520.
Choy, M. C. (2012). US Presidential Election 2012 Prediction using Census Corrected Twitter Model. arXiv preprint arXiv:1211.0938.
Chung, J. E. (2011). Can collective sentiment expressed on twitter predict political elections? AAAI.
Eleições 2014. Pesquisa eleitoral para presidente. Disponível em: http://www.eleicoes2014.com.br/pesquisa-eleitoral-para-presidente/. Acesso em: 10 abr. 2014.
Fink, C. B. (2013). Twitter, Public Opinion, and the 2011 Nigerian Presidential Election. 2013 International Conference on Social Computing (SocialCom). IEEE., 311-320.
Fumagalli, L. &. (2011). The total survey error paradigm and pre-election polls: The case of the 2006 Italian general elections. ISER Working Paper Series. 2011-29.
Gaurav, M. S. (2013). Leveraging candidate popularity on Twitter to predict election outcome. Proceedings of the 7th Workshop on Social Network Mining and Analysis. ACM., 7.
Gayo Avello, D. (2011). Don't turn social media into another'Literary Digest'poll. Communications of the ACM, 54(10), 121-128.
Hillygus, D. S. (2011). The evolution of election polling in the United States. Public opinion quarterly, 75(5),, 962-981.
Jungherr, A. J. (2012). Why the pirate party won the german election of 2009 or the trouble with predictions: A response to tumasjan, a., sprenger, to, sander, pg, & welpe, im “predicting elections with twitter: What 140 characters reveal about political sentiment”. Social Science Computer Review, 30(2),, 229-234.
Lewis-Beck, M. S. (2005). Election forecasting: principles and practice. The British Journal of Politics & International Relations, 7(2),, 145-164.
Makazhanov, A. R. (2014). Predicting political preference of Twitter users. Social Network Analysis and Mining, 1-15.
Mejova, Y. S. (2013). GOP primary season on twitter: popular political sentiment in social media. Proceedings of the sixth ACM international conference on Web search and data mining, 517-526.
Mislove, A. L. (2011). Understanding the Demographics of Twitter Users. ICWSM, 11, 5th.
Nooralahzadeh, F. A. (2013). 2012 Presidential Elections on Twitter--An Analysis of How the US and French Election were Reflected in Tweets. Control Systems and Computer Science (CSCS), 2013 19th International Conference on, 240-246.
O'Connor, B. B. (2010). From tweets to polls: Linking text sentiment to public opinion time series. ICWSM, 11, 122-129.
Paula Filho, W.; GARCIA, A. C. B. RoTuEl: A Semi-Automated Method For Labeling Political. In: Doctoral Consortium at International Joint Conference on Artificial Intelligence (IJCAI-15), 2015, Buenos Aires, Argentina. Proceedings of the Twenty-Four IJCAI.
Prasetyo, N. D. (2014). Tweet-Based Election Prediction (Doctoral dissertation, TU Delft, Delft University of Technology).
Sang, E. T. (2012). Predicting the 2011 dutch senate election results with twitter. the Workshop on Semantic Analysis in Social Media (pp. 53-60). Association for Computational Linguistics.
Tumasjan, A. S. (2010). Predicting Elections with Twitter: What 140 Characters Reveal about Political Sentiment. ICWSM, 10, 178-185.
Wong, F. T. (2013). Media, pundits and the us presidential election: Quantifying political leanings from tweets. In Proceedings of the International Conference on Weblogs and Social Media.
Publicado
01/08/2015
Como Citar
DE PAULA FILHO, Wilton; GARCIA, Ana Cristina.
Predição do resultado das eleições presidenciais do Brasil baseado em tuítes. In: BRAZILIAN WORKSHOP ON SOCIAL NETWORK ANALYSIS AND MINING (BRASNAM), 4. , 2015, Recife.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2015
.
p. .
ISSN 2595-6094.
DOI: https://doi.org/10.5753/brasnam.2015.6782.
