EKİN EKİNCİ, SEVİNÇ İLHAN OMURCA, ESES YAKUPOĞLU, EMİRHAN ARSLAN, BERKAY ÇAPAR

Automatic Detection of the Topics in Customer Complaints with Artificial Intelligence

Today, people first make their complaints and compliments on the internet about a product which they use or a company they are a customer of. Therefore, when they are going to buy a new product, they first analyze the complaints made by other users of the product. These complaints play an important role in helping people make decisions of purchasing or not purchasing products. It is impossible to analyze online complaints manually due to the huge data size. However, companies are still losing a lot of time by analyzing and reading thousands of complaints one by one. In this article, online text based customer complaints are analyzed with Latent Dirichlet Allocation (LDA), GenSim LDA, Mallet LDA and Gibbs Sampling for Dirichlet Multinomial Mixture model (GSDMM) and the performances of them are compared. It is observed that GSDMM gives much more successful results than LDA. The obtained topics of the complaints are presented to users with a mobile application developed in React Native. With the developed application not only the customers will be able to see the topics of complaint from the application interface but also the companies will be able to view the distribution and statistics of the topics of complaints.

PDF

___

[1] S. Prasad, “Use of Natural Language Processing to Improve Complaint Classification in Customer Complaint Management System”, Journal of Critical Reviews, Vol.7, No.14, 2020, pp.2642-2652.
[2] F. Kalyoncu, E. Zeydan, İ. O. Yiğit, A. Yıldırım, “A Customer Complaint Analysis Tool for Mobile Network Operators.” 2018 IEEE/ACM Int. Conf. on Advances in Social Networks Analysis and Mining. Barcelona, Spain, 2018.
[3] R. Liang, W. Guo, D. Yang, “Mining product problems from online feedback of Chinese users”, Kybernetes, Vol.46, No.3, 2017, pp.572- 586.
[4] K. Bastani, N. Hamed, S. Jeffrey, “Latent Dirichlet allocation (LDA) for topic modelling of the CFPB consumer complaints”, Expert System with Applications, Vol.127, 2019, pp.256-271.
[5] W. Mai, M. Wei, J. Zhang, F. Yuan, “Research on Chinese text and application based on the Latent Dirichlet Allocation.” 3rd International Conference on Advanced Electronic Materials, Computers and Software Engineering. Shenzhen, China, 2020.
[6] B. Atıcı, S. İlhan Omurca, E. Ekinci, “Product aspect detection in customer complaints by using latent dirichlet allocation.” 2017 International Conference on Computer Science and Engineering. Antalya, Turkey, 2017.
[7] X. He, H. Xu, X. Sun, J. Deng, X. Bai, J. Li, “Optimize collapsed Gibbs sampling for biterm topic model by alias method.” 2017 International Joint Conference on Neural Networks. Anchorage, Alaska, 2017.
[8] R. Albalawi, T. H. Yeap, M. Benyoucef, “Using Topic Modelling Methods for Short-Text Data: A Comparative Analysis,” Frontiers of Artificial Intelligence, Vol.3, No.42, 2020, pp.1-14.
[9] E. Ekinci, S. İlhan Omurca, “An Aspect-Sentiment Pair Extraction Approach Based on Latent Dirichlet Allocation for Turkish,” International Journal of Intelligent Systems and Applications in Engineering, Vol.6, No.3, 2018, pp.209-213.
[10] D. M. Blei, “Probabilistic topic models,” Communications of ACM, Vol.55, No.4, 2012, pp.77-84.
[11] J. Yin, J. Wang, “A Dirichlet Multinomial Mixture Model-based Approach for Short Text Clustering.” 20th ACM SIGKDD International Joint Conference on Knowledge discovery and data mining. New York, USA, 2014.
[12] C. C. Aggarwal, C. Zhai, Mining text data, Springer, 2012, pp.77-128.
[13] G. Salton, C. S. Yang, C. T. Yu, “A theory of term importance in automatic text analysis”, Journal of the American Society for Information Science, Vol.26, No.1, 1975, pp.33-44.
[14] K. Nigam, A. K. McCallum, S. Thrun, T. M. Mitchell, “Text classification from labeled and unlabeled documents using EM”, Machine Learning, Vol.39, No.2/3, 2000, pp.103-134.
[15] I. Akef, X. Xu, J. S. Munoz Arango “Mallet vs GenSim: Topic modeling for 20 news groups report”, 2016.
[16] P. Stiff, Analysis of Remarks Using Clustering and Keyword Extraction, Master Thesis, 2018, p. 7.