Um Método Baseado em Grafos para Predição da Utilidade de Opiniões sobre Produtos
Resumo
Este trabalho apresenta uma nova abordagem para predição da utilidade de opiniões. Usualmente, os trabalhos nessa área usam tabelas do tipo atributo-valor para agregar as caracterı́sticas que representam os textos avaliados. Neste trabalho, essa tarefa é modelada em forma de rede, considerando, dessa forma, as informações de relacionamento entre os objetos da rede (comentários, estrelas e palavras). Uma técnica de regularização de grafos é utilizada para extrair caracterı́sticas relevantes da estrutura do grafo, e, após isso, os comentários são classificados em duas classes: Útil ou Não Útil. Comparou-se a modelagem com um método baseado em lógica fuzzy e a modelagem apresentou resultados promissores, superando-o em 0,13 pontos na medida F1.
Palavras-chave:
Helpfulness prediction, Opinion mining, Network model
Referências
Anchiêta, R., Sousa, R. F., Moura, R., and Pardo, T. (2017). Improving opinion summari- zation by assessing sentence importance in on-line reviews. In Proceedings of the 11th Brazilian Symposium in Information and Human Language Technology, pages 32–36.
Anchiêta, R. T. and Moura, R. S. (2017). Exploring unsupervised learning towards extrac- tive summarization of user reviews. In Proceedings of the 23rd Brazillian Symposium on Multimedia and the Web, pages 217–220. ACM.
Barbosa, J. L. and Moura, R. S. (2016). Avaliaç ao automática da utilidade de reviews usando redes neurais artificiais no corpus do steam. In Anais do XXVI Congresso da Sociedade Brasileira de Computação: BraSNAM - 5 o Brazilian Workshop on Social Network Analysis and Mining. Brazilian Computer Society.
Bertaglia, T. F. C. and Nunes, M. d. G. V. (2016). Exploring word embeddings for un- supervised textual user-generated content normalization. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pages 112–120.
de Sousa, R. F., Rabêlo, R. A., and Moura, R. S. (2015). A fuzzy system-based approach to estimate the importance of online customer reviews. In Fuzzy Systems (FUZZ- IEEE), 2015 IEEE International Conference on, pages 1–8. IEEE.
Diaz, G. O. and Ng, V. (2018). Modeling and prediction of online product review help- fulness: A survey. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 698–708.
Fonseca, E. R. and Rosa, J. L. G. (2013). Mac-morpho revisited: Towards robust part- of-speech tagging. In Proceedings of the 9th Brazilian symposium in information and human language technology, pages 98–107.
Hartmann, N. S., Avanço, L. V., Balage Filho, P. P., Duran, M. S., Nunes, M. D. G. V., Pardo, T. A. S., Aluisio, S. M., et al. (2014). A large corpus of product reviews in por-tuguese: Tackling out-of-vocabulary words. In International Conference on Language Resources and Evaluation. European Language Resources Association-ELRA.
Kim, S.-M., Pantel, P., Chklovski, T., and Pennacchiotti, M. (2006). Automatically asses- sing review helpfulness. In Proceedings of the 2006 Conference on empirical methods in natural language processing, pages 423–430. Association for Computational Lin- guistics.
Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1):1–167.
Liu, J., Cao, Y., Lin, C.-Y., Huang, Y., and Zhou, M. (2007). Low-quality product review detection in opinion summarization. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL).
Malik, M. and Hussain, A. (2017). Helpfulness of product reviews as a function of dis- crete positive and negative emotions. Computers in Human Behavior, 73:290–302.
Martins, A. C. S. and Tacla, C. A. (2015). Assessement of features influencing the voting for opinions’ helpfulness about services in portuguese. In Proceedings of the annual conference on Brazilian Symposium on Information Systems: Information Systems: A Computer Socio-Technical Perspective-Volume 1, page 21. Brazilian Computer Soci- ety.
Orengo, V. and Huyck, C. (2001). A stemming algorithmm for the portuguese language. In String Processing and Information Retrieval, pages 186–193.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Rossi, R. G. (2016). Classificação automática de textos por meio de aprendizado de máquina baseado em redes. PhD thesis, Universidade de São Paulo.
Santos, R. L. d. S., de Sousa, R. F., Rabelo, R. A., and Moura, R. S. (2016). An expe- rimental study based on fuzzy systems and artificial neural networks to estimate the importance of reviews about product and services. In Neural Networks (IJCNN), 2016 International Joint Conference on, pages 647–653. IEEE.
Scarton, C. E. and Aluı́sio, S. M. (2010). Análise da inteligibilidade de textos via ferra- mentas de processamento de lı́ngua natural: adaptando as métricas do coh-metrix para o português. Linguamática, 2(1):45–61.
Singh, J. P., Irani, S., Rana, N. P., Dwivedi, Y. K., Saumya, S., and Roy, P. K. (2017). Pre- dicting the “helpfulness” of online consumer reviews. Journal of Business Research, 70:346–355.
Zhu, X., Ghahramani, Z., and Lafferty, J. D. (2003). Semi-supervised learning using gaus- sian fields and harmonic functions. In Proceedings of the 20th International conference on Machine learning (ICML-03), pages 912–919.
Anchiêta, R. T. and Moura, R. S. (2017). Exploring unsupervised learning towards extrac- tive summarization of user reviews. In Proceedings of the 23rd Brazillian Symposium on Multimedia and the Web, pages 217–220. ACM.
Barbosa, J. L. and Moura, R. S. (2016). Avaliaç ao automática da utilidade de reviews usando redes neurais artificiais no corpus do steam. In Anais do XXVI Congresso da Sociedade Brasileira de Computação: BraSNAM - 5 o Brazilian Workshop on Social Network Analysis and Mining. Brazilian Computer Society.
Bertaglia, T. F. C. and Nunes, M. d. G. V. (2016). Exploring word embeddings for un- supervised textual user-generated content normalization. In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pages 112–120.
de Sousa, R. F., Rabêlo, R. A., and Moura, R. S. (2015). A fuzzy system-based approach to estimate the importance of online customer reviews. In Fuzzy Systems (FUZZ- IEEE), 2015 IEEE International Conference on, pages 1–8. IEEE.
Diaz, G. O. and Ng, V. (2018). Modeling and prediction of online product review help- fulness: A survey. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 698–708.
Fonseca, E. R. and Rosa, J. L. G. (2013). Mac-morpho revisited: Towards robust part- of-speech tagging. In Proceedings of the 9th Brazilian symposium in information and human language technology, pages 98–107.
Hartmann, N. S., Avanço, L. V., Balage Filho, P. P., Duran, M. S., Nunes, M. D. G. V., Pardo, T. A. S., Aluisio, S. M., et al. (2014). A large corpus of product reviews in por-tuguese: Tackling out-of-vocabulary words. In International Conference on Language Resources and Evaluation. European Language Resources Association-ELRA.
Kim, S.-M., Pantel, P., Chklovski, T., and Pennacchiotti, M. (2006). Automatically asses- sing review helpfulness. In Proceedings of the 2006 Conference on empirical methods in natural language processing, pages 423–430. Association for Computational Lin- guistics.
Liu, B. (2012). Sentiment analysis and opinion mining. Synthesis lectures on human language technologies, 5(1):1–167.
Liu, J., Cao, Y., Lin, C.-Y., Huang, Y., and Zhou, M. (2007). Low-quality product review detection in opinion summarization. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL).
Malik, M. and Hussain, A. (2017). Helpfulness of product reviews as a function of dis- crete positive and negative emotions. Computers in Human Behavior, 73:290–302.
Martins, A. C. S. and Tacla, C. A. (2015). Assessement of features influencing the voting for opinions’ helpfulness about services in portuguese. In Proceedings of the annual conference on Brazilian Symposium on Information Systems: Information Systems: A Computer Socio-Technical Perspective-Volume 1, page 21. Brazilian Computer Soci- ety.
Orengo, V. and Huyck, C. (2001). A stemming algorithmm for the portuguese language. In String Processing and Information Retrieval, pages 186–193.
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830.
Rossi, R. G. (2016). Classificação automática de textos por meio de aprendizado de máquina baseado em redes. PhD thesis, Universidade de São Paulo.
Santos, R. L. d. S., de Sousa, R. F., Rabelo, R. A., and Moura, R. S. (2016). An expe- rimental study based on fuzzy systems and artificial neural networks to estimate the importance of reviews about product and services. In Neural Networks (IJCNN), 2016 International Joint Conference on, pages 647–653. IEEE.
Scarton, C. E. and Aluı́sio, S. M. (2010). Análise da inteligibilidade de textos via ferra- mentas de processamento de lı́ngua natural: adaptando as métricas do coh-metrix para o português. Linguamática, 2(1):45–61.
Singh, J. P., Irani, S., Rana, N. P., Dwivedi, Y. K., Saumya, S., and Roy, P. K. (2017). Pre- dicting the “helpfulness” of online consumer reviews. Journal of Business Research, 70:346–355.
Zhu, X., Ghahramani, Z., and Lafferty, J. D. (2003). Semi-supervised learning using gaus- sian fields and harmonic functions. In Proceedings of the 20th International conference on Machine learning (ICML-03), pages 912–919.
Publicado
09/07/2019
Como Citar
DE SOUSA, Rogério F.; ANCHIETA, Rafael T. ; NUNES, Maria das Graças V. .
Um Método Baseado em Grafos para Predição da Utilidade de Opiniões sobre Produtos. In: BRAZILIAN WORKSHOP ON SOCIAL NETWORK ANALYSIS AND MINING (BRASNAM), 8. , 2019, Belém.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 95-106.
ISSN 2595-6094.
DOI: https://doi.org/10.5753/brasnam.2019.6552.
