Tweet Sentiment Analysis Regarding the Brazilian Stock Market
Resumo
Este artigo descreve uma metodologia para análise de sentimentos e para descoberta de conhecimento em tweets sobre o mercado acionário brasileiro. A metodologia proposta começa com o pré-processamento e a caracterização de tweets para obter um modelo de espaço vetorial associado. Depois disso, uma redução de dimensionalidade é empregada usando a Análise de Componentes Principais e o Emprego de Vizinhos T-Estocásticos. A análise do sentimento dos tweets do mercado de ações é realizada considerando as tarefas de classificação de sentimento, modelagem de tópico e agrupamento, juntamente com um processo de análise visual. Os resultados dos experimentos mostraram desempenhos satisfatórios em cenários de classificação de sentimento simples e multi-rótulo. O processo de análise visual também revelou relações interessantes entre tópicos e clusters.
Referências
Altrabsheh, N., Cocea, M., and Fallahkhair, S. (2014). Sentiment analysis: towards a tool for analysing real-time students feedback. In IEEE 26th Inter- national Conference on Tools with Artificial Intelligence, pages 419–423. IEEE.
Barberá, P. and Rivero, G. (2015). Understanding the political representativeness of twitter users. Social Science Computer Review, 33(6):712–729.
Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet alloca- tion. Journal of Machine Learning Research, 3(Jan):993–1022.
Bollen, J. and Mao, H. (2011). Twitter mood as a stock market predictor. Computer, 44:91–94.
Clark, E. M., James, T., Jones, C. A., Alapati, A., Ukandu, P., Danforth, C. M., and Dodds, P. S. (2018). A sentiment analysis of breast cancer treatment expe- riences and healthcare perceptions across twitter. arXiv preprint arXiv:1805.09959.
Galdi, F. C. and Gonçalves, A. M. (2018). Pessimism and un- certainty of the news and investor behavior in brazil. RAE-Revista de Administração de Empresas (Journal of Business Management), 58(2):130–148.
Giachanou, A. and Crestani, F. (2016). Like it or not: A sur- vey of twitter sentiment analysis methods. ACM Computing Surveys (CSUR), 49(2):28.
Gillis, N. (2014). The why and how of nonnegative matrix factorization. Reg- ularization, Optimization, Kernels, and Support Vector Machines, 12.
Jolliffe, I. (2011). Principal component analysis. Springer.
Li, H., Cui, J., Shen, B., and Ma, J. (2016). An intelligent movie recommen- dation system through group-level sentiment analysis in microblogs. Neurocomputing, 210:164–173.
L.Lima, M., P. Nascimento, T., Labidi, S., S. Timbo, N., V. L. Batista, M., N. Neto, G., A. M. Costa, E., and R. S. Sousa, S. (2016). Using sentiment anal- ysis for stock exchange prediction. International Journal of Artificial Intelligence & Applications, 7:59–67.
Maaten, L. v. d. and Hinton, G. (2008). Visualizing data using t-sne. Journal of machine learning research, 9(Nov):2579–2605.
Pauca, V. P., Shahnaz, F., Berry, M. W., and Plemmons, R. J. (2004). Text mining using non-negative matrix factorizations. In Proceedings of the 2004 SIAM International Conference on Data Mining, pages 452–456. SIAM.
Paulovich, F. V., Oliveira, M. C. F., and Minghim, R. (2007). The projection explorer: A flexible tool for projection-based multidimensional visualiza- tion. In XX Brazilian Symposium on Computer Graphics and Image Processing (SIB- GRAPI 2007), pages 27–36.
Plutchik, R. (1980). Emotion: A Psychoevolutionary Synthesis. Harper and Row.
Rao, T. and Srivastava, S. (2012). Analyzing stock market move- ments using twitter sentiment analysis. In Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2012), ASONAM ’12, pages 119–123, Washington, DC, USA. IEEE Computer Society.
Silva, F. V. d. (2018). Brazilian stock market tweets with emotions.
Smailović, J., Grčar, M., Lavrač, N., and Žnidaršič, M. (2013). Pre- dictive sentiment analysis of tweets: A stock market application. In Holzinger, A. and Pasi, G., editors, Human-Computer Interaction and Knowledge Discovery in Complex, Unstructured, Big Data, pages 77–88, Berlin, Heidelberg. Springer Berlin Heidelberg.
Zimek, A., Schubert, E., and Kriegel, H.-P. (2012). A survey on unsu- pervised outlier detection in high-dimensional numerical data. Statistical Analysis and Data Mining: The ASA Data Science Journal, 5(5):363–387.
Barberá, P. and Rivero, G. (2015). Understanding the political representativeness of twitter users. Social Science Computer Review, 33(6):712–729.
Blei, D. M., Ng, A. Y., and Jordan, M. I. (2003). Latent dirichlet alloca- tion. Journal of Machine Learning Research, 3(Jan):993–1022.
Bollen, J. and Mao, H. (2011). Twitter mood as a stock market predictor. Computer, 44:91–94.
Clark, E. M., James, T., Jones, C. A., Alapati, A., Ukandu, P., Danforth, C. M., and Dodds, P. S. (2018). A sentiment analysis of breast cancer treatment expe- riences and healthcare perceptions across twitter. arXiv preprint arXiv:1805.09959.
Galdi, F. C. and Gonçalves, A. M. (2018). Pessimism and un- certainty of the news and investor behavior in brazil. RAE-Revista de Administração de Empresas (Journal of Business Management), 58(2):130–148.
Giachanou, A. and Crestani, F. (2016). Like it or not: A sur- vey of twitter sentiment analysis methods. ACM Computing Surveys (CSUR), 49(2):28.
Gillis, N. (2014). The why and how of nonnegative matrix factorization. Reg- ularization, Optimization, Kernels, and Support Vector Machines, 12.
Jolliffe, I. (2011). Principal component analysis. Springer.
Li, H., Cui, J., Shen, B., and Ma, J. (2016). An intelligent movie recommen- dation system through group-level sentiment analysis in microblogs. Neurocomputing, 210:164–173.
L.Lima, M., P. Nascimento, T., Labidi, S., S. Timbo, N., V. L. Batista, M., N. Neto, G., A. M. Costa, E., and R. S. Sousa, S. (2016). Using sentiment anal- ysis for stock exchange prediction. International Journal of Artificial Intelligence & Applications, 7:59–67.
Maaten, L. v. d. and Hinton, G. (2008). Visualizing data using t-sne. Journal of machine learning research, 9(Nov):2579–2605.
Pauca, V. P., Shahnaz, F., Berry, M. W., and Plemmons, R. J. (2004). Text mining using non-negative matrix factorizations. In Proceedings of the 2004 SIAM International Conference on Data Mining, pages 452–456. SIAM.
Paulovich, F. V., Oliveira, M. C. F., and Minghim, R. (2007). The projection explorer: A flexible tool for projection-based multidimensional visualiza- tion. In XX Brazilian Symposium on Computer Graphics and Image Processing (SIB- GRAPI 2007), pages 27–36.
Plutchik, R. (1980). Emotion: A Psychoevolutionary Synthesis. Harper and Row.
Rao, T. and Srivastava, S. (2012). Analyzing stock market move- ments using twitter sentiment analysis. In Proceedings of the 2012 International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2012), ASONAM ’12, pages 119–123, Washington, DC, USA. IEEE Computer Society.
Silva, F. V. d. (2018). Brazilian stock market tweets with emotions.
Smailović, J., Grčar, M., Lavrač, N., and Žnidaršič, M. (2013). Pre- dictive sentiment analysis of tweets: A stock market application. In Holzinger, A. and Pasi, G., editors, Human-Computer Interaction and Knowledge Discovery in Complex, Unstructured, Big Data, pages 77–88, Berlin, Heidelberg. Springer Berlin Heidelberg.
Zimek, A., Schubert, E., and Kriegel, H.-P. (2012). A survey on unsu- pervised outlier detection in high-dimensional numerical data. Statistical Analysis and Data Mining: The ASA Data Science Journal, 5(5):363–387.
Publicado
09/07/2019
Como Citar
MEDEIROS, Murilo C.; BORGES, Vinicius R. P..
Tweet Sentiment Analysis Regarding the Brazilian Stock Market. In: BRAZILIAN WORKSHOP ON SOCIAL NETWORK ANALYSIS AND MINING (BRASNAM), 8. , 2019, Belém.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 71-82.
ISSN 2595-6094.
DOI: https://doi.org/10.5753/brasnam.2019.6550.
