Identification and Categorization of Complaints in Comments about Companies in the Sports Betting Sector

• Tobias de Abreu Kuse UCS
• Helena Graziottin Ribeiro UCS

DOI: https://doi.org/10.5753/erbd.2024.238765

Abstract

A significant part of the comments on sports betting company profiles refer to complaints and problems reported by customers. The present work tested supervised learning methods to classify comments as complains in data collected from Instagram, using the SVM model. Topic modeling techniques were applied to comments classified as complaints, and the GSDMM algorithm was selected, making it possible to obtain the main problems reported by users. The selected models were implemented in an online prototype that allows the insertion and analysis of new comments.

References

Ohata, E. F., Mattos, C. L. C., Gomes, S. L., Rebouças, E. D. S., and Rego, P. A. L. (2022). A text classification methodology to assist a large technical support system. IEEE Access, 10:108413–108421.

Parmar, P. S., Biju, P. K., Shankar, M., and Kadiresan, N. (2018). Multiclass text classification and analytics for improving customer support response through different classifiers. In 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), pages 538–542.

Qiang, J., Qian, Z., Li, Y., Yuan, Y., and Wu, X. (2022). Short text topic modeling techniques, applications, and performance: A survey. IEEE Transactions on Knowledge and; Data Engineering, 34(03):1427–1445.

Yin, J. and Wang, J. (2014). A dirichlet multinomial mixture model-based approach for short text clustering. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’14, page 233–242, New York, NY, USA. Association for Computing Machinery.

İLHAN OMURCA, S., EKİNCİ, E., YAKUPOĞLU, E., ARSLAN, E., and ÇAPAR, B. (2021). Automatic detection of the topics in customer complaints with artificial intelligence. Balkan Journal of Electrical and Computer Engineering, 9(3):268–277.