Phân tích ý kiến khách hàng trong thương mại điện tử –  Tiếp cận theo phương pháp học máy kết hợp kiểm định Bootstrap

Thành Hồ Trung; Ánh Trần Thị; Tuyền Huỳnh Thanh

doi:10.24311/jabes/2020.31.11.4

Authors

Thành Hồ Trung Trường Đại học Kinh tế - Luật, Đại học Quốc Gia TP. Hồ Chí Minh Author
Ánh Trần Thị Trường Đại học Kinh tế - Luật, Đại học Quốc Gia TP. Hồ Chí Minh Author
Tuyền Huỳnh Thanh Trường Đại học Kinh tế - Luật, Đại học Quốc Gia TP. Hồ Chí Minh Author

DOI:

https://doi.org/10.24311/jabes/2020.31.11.4

Keywords:

SOM, K-Means, Bootstrap method, Natural language processing, Online customer reviews, E-commerce

Abstract

The development of the Web 2.0 generation has created an opportunity for interaction between customers and businesses through e-commerce channels more effectively. Customers can post feedbacks by leaving textual comments that are the natural language in Vietnamese related to products or services which they have experienced. As a result, businesses can manage and analyze opinions to deeply understand the customers' experiences to attract and retain their customers. This is an important and effective approach for businesses to create a competitive advantage. In this article, the authors concentrate on proposing a method of analyzing customers' opinions based on the natural language processing method which is combined with Self-Organizing Map (SOM) and K-Means. In addition, the T-test technique with the Bootstrap method is applied to evaluate the results in order to select the appropriate clustering method for the case of a dataset that is collected from customers' feedbacks of Tiki's e-commerce site. The proposed method has high accuracy and effective applicability to customer experience analysis.

References

Jaye, A. B., Bruyère, C. L., & Done, J. M. (2019). Understanding future changes in tropical cyclogenesis using Self-Organizing Maps. Weather and Climate Extremes, 26, 100235. doi: 10.1016/j.wace.2019.100235

Ettaouil, M., Lazaar, M., Elmoutaouakil, K., & Glanou, Y. (2011). A new architecture optimization model for the Kohonen networks and clustering. Journal of Advanced Research, 3(1), 14–32.

Honkela, T., Kaski, S., Lagus, K., & Kohonen, T. (1997). Websom-self-organizing maps of document collections. Proceedings of the Work shop on Self-Organizing Maps (WSOM '97) (pp. 310–315), Espoo, Finland.

Jolliffe, I. T., & Cadima, J. (2016). Principal component analysis: A review and recent developments. Philosophical transactions of the Royal society A Mathematical Physical and Engineering Sciences, 374(2065). doi: 10.1098/rsta.2015.0202

Kaski, S., Honkela, T., Lagus, K., & Kohonen, T. (1998). Websom-self-organizing maps of document collections. Neurocomputing, 21(1–3), 101–117.

Kohonen, T. (1995). Self-Organizing Maps. Berlin: Spinger-Verlag.

Kohonen, T. (2013). Essentials of the self-organizing map. Neural Networks, 37, 52–65.

Kohonen, T., Kaski, S., Lagus, K., Salojarvi, J., Honkela, J., Paatero, V., & Saarela, A. (2000). Self organization of a massive document collection. IEEE Transactions on Neural Networks, 11(3), 574–585.

Kumar, V. (2016). Introduction: Is Customer Satisfaction (Ir)relevant as a Metric?. Journal of Marketing, 80(5), 108–109. doi:10.1509/jm.80.5.1

Lin, G., & Li, S. (2009). Clustering method using hypergraph models based on Set Pair Analysis. 2009 IEEE International Symposium on IT in Medicine & Education (1194–1197). doi: 10.1109/ITIME.2009.5236279

Liu, Y.-C., Liu, M., & Wang, X.-L. (2012). Application of self-organizing maps in text clustering: A review. In M. Johnsson (Ed.), Applications of Self-Organizing Maps (Chapter 10). Rijeka: InTech.

Michalski, R. S., Bratko, I., & Kubat, M. (1999). Machine Learning And Data Mining Methods And Applications. Wiley

Nakano, T., Nagai, S., Yamatogi, T., Kunhara, T., & Okamura, K. (2020). Use of sea surface discoloration to monitor and discriminate the causative genera of harmful algal blooms (HABs): Practical use of digital repeat photography. Ecological Informatics, 59. doi: /10.1016/j.ecoinf.2020.101114

Ultsch, A., & Herrmann, L. (2005). The Architecture of Emergent Self-Organizing Maps to Reduce Projection Errors. ESANN 2005, 13th European Symposium on Artificial Neural Networks, Bruges, Belgium.

Rumelhart, D. E., & Zipser, D. (1985). Feature discovery by competitive learning. Cognitive Science, 9, 75–112.

Syakur, M. A., Khotimah, B. K., Rochman, E. M. S., & Satoto, B. D. (2018). Integration k-means clustering method and elbow method for identification of the best customer profile cluster. IOP Conference Series: Materials Science and Engineering, 336(1). Retrieved from https://iopscience.iop.org/article/10.1088/1757-899X/336/1/012017

Till, B. C., Longo, J., Dobell, A. R., & Driessen, P. F. (2014). Self-organizing maps for latent semantic analysis of free-form text in support of public policy analysis. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 4(1), 71–86.

Thanh, H., & Phuc, D. (2015). Discovering Communities of Users on Social Networks Based on Topic Model Combined with Kohonen Network. 2015 Seventh International Conference on Knowledge and Systems Engineering (KSE) (pp. 268-273). doi: 10.1109/KSE.2015.54

Thanh, H. T., Hung, N. Q., & Thanh, T. D. (2019). Applying topic model combined with Kohonen networks to discover and visualize communities on social networks. Science & Technology Development Journal-Economics-Law and Management, 3(3), 311–326.

Yen, G. G., & Wu, Z. (2008). Ranked Centroid Projection: A Data Visualization Approach with Self-Organizing Maps. IEEE Transactions on Neural Networks, 19(2), 245–259.

Zhu, J., & Liu, S. (2014). SOM network-based clustering analysis of real estate enterprises. American Journal of Industrial and Business Management, 4(3), 167–173.