Análise de Sentimentos em Vídeos do Youtube sobre Polarização Política: Uma Abordagem Híbrida Baseada em Reconhecimento de Entidades
Resumo
Neste trabalho, análises de sentimentos em nível de sentença são empregadas com o modelo BERTimbau, a fim de comparar o conteúdo de videos do Youtube, considerando a polarização política no Brasil em dois períodos: durante e após as eleições presidenciais brasileiras de 2022. Os dois principais candidatos foram identificados como entidades a partir das transcrições dos vídeos. Foi proposta ainda a métrica Score para normalizar os resultados. Os dados indicaram uma maior presença do candidato Bolsonaro no YouTube, principalmente em canais jornalísticos, e também foi possível identificar mudanças de posicionamento nestes canais entre os dois períodos.
Referências
Buder, J., Rabl, L., Feiks, M., Badermann, M., and Zurstiege, G. (2021). Does negatively toned language use on social media lead to attitude polarization? Computers in Human Behavior, 116:106663.
Gu, S., Zhang, L., Hou, Y., and Song, Y. (2018). A position-aware bidirectional attention network for aspect-level sentiment analysis. In Proceedings of the 27th international conference on computational linguistics, pages 774–784.
Kubin, E. and von Sikorski, C. (2021). The role of (social) media in political polarization: a systematic review. Annals of the International Communication Association, 45(3):188–206.
Liu, K., Xu, L., and Zhao, J. (2012). Opinion target extraction using word-based translation model. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, page 1346–1356.
Mohit, B. (2014). Named entity recognition. In Natural language processing of semitic languages, pages 221–245. Springer.
Newman, N., Fletcher, R., Robertson, C. T., Eddy, K., and Nielsen, R. K. (2022). Reuters institute digital news report 2022. In Reuters Institute Digital News Report 2022, pages 116–117.
Poria, S., Hazarika, D., Majumder, N., and Mihalcea, R. (2020). Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research. IEEE Transactions on Affective Computing.
Salas-Zárate, M. d. P., Medina-Moreira, J., Lagos-Ortiz, K., Luna-Aveiga, H., Rodriguez-Garcia, M. A., and Valencia-Garcia, R. (2017). Sentiment analysis on tweets about diabetes: an aspect-level approach. Computational and mathematical methods in medicine, 2017.
Sharnagat, R. (2014). Named entity recognition: A literature survey. Center For Indian Language Technology, pages 1–27.
Silva, C. A. and Barbosa, D. M. (2019). Analyzing the acceptance of the 2018 brazilian presidential election’main candidates based on youtube comments. In Proceedings of the 25th Brazillian Symposium on Multimedia and the Web, pages 377–384.
Souza, F., Nogueira, R., and Lotufo, R. (2019). Portuguese named entity recognition using bert-crf. arXiv preprint arXiv:1909.10649.
Wagner Filho, J. A., Wilkens, R., Idiart, M., and Villavicencio, A. (2018). The brwac corpus: a new open resource for brazilian portuguese. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018).
Gu, S., Zhang, L., Hou, Y., and Song, Y. (2018). A position-aware bidirectional attention network for aspect-level sentiment analysis. In Proceedings of the 27th international conference on computational linguistics, pages 774–784.
Kubin, E. and von Sikorski, C. (2021). The role of (social) media in political polarization: a systematic review. Annals of the International Communication Association, 45(3):188–206.
Liu, K., Xu, L., and Zhao, J. (2012). Opinion target extraction using word-based translation model. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, page 1346–1356.
Mohit, B. (2014). Named entity recognition. In Natural language processing of semitic languages, pages 221–245. Springer.
Newman, N., Fletcher, R., Robertson, C. T., Eddy, K., and Nielsen, R. K. (2022). Reuters institute digital news report 2022. In Reuters Institute Digital News Report 2022, pages 116–117.
Poria, S., Hazarika, D., Majumder, N., and Mihalcea, R. (2020). Beneath the tip of the iceberg: Current challenges and new directions in sentiment analysis research. IEEE Transactions on Affective Computing.
Salas-Zárate, M. d. P., Medina-Moreira, J., Lagos-Ortiz, K., Luna-Aveiga, H., Rodriguez-Garcia, M. A., and Valencia-Garcia, R. (2017). Sentiment analysis on tweets about diabetes: an aspect-level approach. Computational and mathematical methods in medicine, 2017.
Sharnagat, R. (2014). Named entity recognition: A literature survey. Center For Indian Language Technology, pages 1–27.
Silva, C. A. and Barbosa, D. M. (2019). Analyzing the acceptance of the 2018 brazilian presidential election’main candidates based on youtube comments. In Proceedings of the 25th Brazillian Symposium on Multimedia and the Web, pages 377–384.
Souza, F., Nogueira, R., and Lotufo, R. (2019). Portuguese named entity recognition using bert-crf. arXiv preprint arXiv:1909.10649.
Wagner Filho, J. A., Wilkens, R., Idiart, M., and Villavicencio, A. (2018). The brwac corpus: a new open resource for brazilian portuguese. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018).
Publicado
21/07/2024
Como Citar
PEREIRA, Iury M.; AVELAR, Juan Pablo A.; SILVA, Cláudio B.; BARBOSA, Daniel M..
Análise de Sentimentos em Vídeos do Youtube sobre Polarização Política: Uma Abordagem Híbrida Baseada em Reconhecimento de Entidades. In: BRAZILIAN WORKSHOP ON SOCIAL NETWORK ANALYSIS AND MINING (BRASNAM), 13. , 2024, Brasília/DF.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2024
.
p. 221-227.
ISSN 2595-6094.
DOI: https://doi.org/10.5753/brasnam.2024.2954.
