All Issue

2024 Vol.12, Issue 1 Preview Page

Research Article

Customer Experience Improvement Initiative based on the Topic Modeling Analysis of Purchase Reviews

구매후기 토픽모델링 분석 기반 고객경험 증진 제안 연구

Hanjin Lee1, Yeeun Lee2, and Suhyun Park3

이한진1, 이예은2, 박수현3

1Assistant Professor, School of Creative Convergence, Handong Global University
2Research Assistant, Department of ICT Entrepreneurship, Handong Global University
3Research Assistant, Graduate School of Computer Science and Electrical Engineering, Handong Global University
1한동대학교 창의융합교육원 조교수
2한동대학교 ICT창업학부 전공 연구조교
3한동대학교 일반대학원 전산전자공학부 연구조교
31 March 2024. pp. 77-88
PDF Citation
Abstract
전 세계적으로 온라인 식료품 구매가 지속적으로 증가함에 따라 소비자 후기는 구매행동에 큰 영향을 주고, 이를 효과적으로 분석하면 고객경험을 향상시킬 수 있을 것이다. 이에 본 연구에서는 토픽모델링을 활용하여 고객 리뷰를 분석하고, 상품군 특성에 따른 구매동기를 파악하고자 한다. MeCab 한국어 형태소 분석 알고리즘과 불용어처리를 활용하여 국내 대표 식품구매 플랫폼에서 21~22년, 24개월간 약 120만 개의 리뷰 데이터셋을 전처리하였다. 단순한 ‘좋다’, ‘만족스럽다’, ‘추천한다’와 같은 범용어 외에 의미 있는 단어를 추출하고자 테스트 데이터셋 기반 성능을 비교하기 위해 BERTopic, LDA, CTM의 3가지 토픽모델링 유형을 적용하였다. 분석 결과, CTM은 79,616개의 유효한 데이터군에서 배송 현황, 제품 특성, 레시피 정보 등 3가지의 관련 토픽을 안정적 추출하여 가장 우수한 성능을 보였다. 이는 가치 있는 제품과 구매 통찰력을 제공하는 것을 기반으로 고객경험을 향상하는 데 학술적, 기술적 시사점을 제공한다.
As online grocery purchases continue to rise globally after pandemic, consumer reviews have gained significant influence over purchasing behavior. Analyzing user reviews in-depth and providing valuable information from the customer’s perspective has become crucial for improving the customer experience. This research project aims to analyze customer reviews using topic modeling to identify product group characteristics and purchase motives. A dataset of about 1.2 million reviews from Jan. 2021 to Dec. 2022, obtained from Korea’s leading food purchasing platform, was pre-processed using the MeCab Korean morpheme analysis algorithm. Researchers want to overcome the challenge of extracting such insights from general-purpose words like ‘good,’ ‘satisfaction,’ and ‘recommendation.’ Three types of topic modeling—BERTopic, LDA, and CTM—were applied to compare their performance on a test dataset. Finally CTM demonstrated the best performance and successfully extracted three relevant topics from the 79,616 valid review dataset: delivery status, product characteristics, and recipe-related topics. Analysis results offer academic and technical implications for improving customer experience based on providing valuable product and purchasing insights.
Keywords
Mobile grocery shopping
Combined topic modeling
BERTopic
LDA
Customer experience
Review helpfulness
References
  1. eMarketer, "2022 Total Retail Sales Worldwide", www.insiderintelligence.com (accessed December 31, 023).
  2. KREI, "Food Consumption Behavior Survey Report 2024", pp. 5-19,www.krei.re.kr (accessed March 23, 024).
  3. Statistics Korea, "2023 Annual Online Shopping Trends", pp. 1-15, www.kostat.go.kr (accessed March 23, 024).
  4. OpenSurvey, "2023 Online Grocery Buying Trends Report", pp. 3-17,www.opensurvey.com (accessed February 3, 2024).
  5. H.J. Lee, S.Y. Kwon, and D.H. Min, "The Empirical Research on the User Satisfaction of Mobile Grocery Shopping Customer Journey", Journal of Information Technology Applications & Management(JITAM), Vol. 28, No. 4, pp. 59-78, 2021.
  6. Consumers Union of Korea, "Survey Results on the Status and Aware of Consumption", www.cuk.or.kr (accessed March 7, 2024).
  7. R. Rietsche, D. Frei, E. Stoeckli, and M. Söllne, "Not All Reviews are Equal - a Literature Review on Online Review Helpfulness", In Proceedings of the 27th European Conference on Information Systems (ECIS), Stockholm & Uppsala, Sweden, pp. 1-18, 2019.
  8. K. Zhao., A. C. Stylianou, and Y. Zheng, "Sources and impacts of social influence from online anonymous user reviews", Information & Management, Vol. 55, No. 11, pp. 16-30, 2018.10.1016/j.im.2017.03.006
  9. S. M. Mudambi, and D. Schuff, "What makes a helpful online review? A study of customer reviews on Amazon.com", MIS Quarterly, Vol. 34, No. 1, pp. 185-200, 2010. 10.2307/20721420
  10. M. Li, L. Huang, C. Tan, and K. Wei, "Helpfulness of online product reviews as seen by consumers: Source and content features", International Journal of Electronic Commerce(IJEC), Vol. 17, No. 4, pp. 101-136, 2013. 10.2753/JEC1086-4415170404
  11. H. G. Lee, and H. Gwak, "A Study on the Factors Influencing the Effectiveness of Online Consumer Reviews and Informatization Policy", Korea Intelligence Society Agency(KISA), Vol. 20, No. 3, pp. 3-17, 2013.
  12. K. Saleh, "The Importance of Online Customer Reviews", retrieved from www.invespcro.com/blog/the-importance-of-online- customer-reviews-infographic (accessed June 10 2023)
  13. S. W. Ahn, "Effects of Customer Rating and Review on Purchase Intention of Experience Product: Moderating Effects of Preference Similarity and Preference Differentiation", Korean Society of Consumer Studies, Vol. 33, No. 4, pp. 1-25, 2022.10.35736/JCS.33.4.1
  14. J. Han, and J. S. Kim, "The Effect of Review Attributes on Brand Attitude, Purchase Decision and e-WOM Intention in Online Shopping Mall", The Society of Digital Policy & Management(SDPM), Vol. 19, No. 7, pp. 113-127, 2021.
  15. F. Zhu, and X. Zhang, "Impact of online consumer reviews on sales: The moderating role of product and consumer characteristics", Journal of Marketing, Vol. 74, No. 2, pp. 133-148, 2010. 10.1509/jmkg.74.2.133
  16. W. Chu, and M. Roh, "Exploring the Role of Preference Heterogeneity and Causal Attribution in Online Rating Dynamics", Asia Marketing Journal, Vol. 15, No. 4, pp. 61-101, 2014. 10.53728/2765-6500.1567
  17. J. Kim, and S. J. Lennon, "Effects of reputation and website quality on online consumers' emotion, perceived risk and purchase intention", Journal of Research in Interactive Marketing(JRIM), Vol. 7, No. 1, pp. 33-56, 2013. 10.1108/17505931311316734
  18. Z. Jiang, and I. Benbasat, "Virtual product experience: Effects of visual and functional control of products on perceived diagnosticity and flow in electronic shopping", Journal of Management Information Systems, Vol. 21, No. 3, pp. 111-147, 2004. 10.1080/07421222.2004.11045817
  19. P. A. Pavlou, H. Liang, and Y. Xue, "Understanding and mitigating uncertainty in online exchange relationships: A principal-agent perspective", MIS Quarterly, Vol. 31, No. 1, pp. 105-136, 2007. 10.2307/25148783
  20. M. Grootendorst, "BERTopic: Neural topic modeling with a class-based TF-IDF procedure", arXiv eprint, arXiv:2203.05794, https://arxiv.org/abs/2203.05794, Vol. 1, 2022.
  21. F. Bianchi, S. Terragni, and D. Hovy, "Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence", Association for Computational Linguistics, Vol. 2, pp. 759-766, 2021.10.18653/v1/2021.acl-short.9634230438
  22. J. Devlin, M. Y. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding", arXiv preprint, arXiv:1810.04805. https://arxiv.org/abs/1810.04805, Vol. 1, 2018.
  23. D. M. Blei, A. Y. Ng, and M. I. Jordan. "Latent Dirichlet Allocation", Journal of Machine Learning Research, Vol. 1, 2003.
  24. FAO STAT, https://faostat.fao.org (accessed December 21, 2023)
  25. J. Chuang, C. D. Manning, and J. Heer, "Termite: Visualization Techniques for Assessing Textual Topic Models", Proceedings of the International Working Conference on Advanced Visual Interfaces, pp. 74-77, 2012.10.1145/2254556.2254572PMC3281944
  26. C. Sievert, and K. E. Shirley, "LDAvis: A method for visualizing and interpreting topics", Proceedings of the Workshop on Interactive Language Learning, Visualization, and Interfaces, pp. 63-70, 2014.10.3115/v1/W14-311024684756
  27. Y. G. Park, D. H. Min, and H. J. Lee, "The Effect of Live Broadcast of Fresh Food on Customer's Purchasing Intention", The Journal of Industrial Distribution & Business, Vol. 14, No.9, pp. 31-39, 2023.
  28. J. H. Kim, Y. B. Ko, J. H. Choi, and H. J. Lee, "Research on the Design of a Deep Learning-Based Automatic Web Page Generation System", Journal of The Korea Society of Computer and Information (JKSCI), Vol. 29, No. 2, pp. 21-30, 2024.
  29. H. Lee, Y. G. Park, and D. H. Min, "Analysis of Factors Affecting the Continuance Intention to Use Mobile Grocery Shopping", The Journal of Information Systems, Vol. 29, No. 2, pp. 95-110, 2020.
  30. S. H. Park, Y. E. Lee, and H. J. Lee, "Research on Enhancing Customer Experience through AI-Supported Review Generation", Transactions of The Korean Institute of Electrical Engineers(TKIEE), Vol. 73, No. 2, pp. 334-342, 2024.10.5370/KIEE.2024.73.2.334
Information
  • Publisher :The Society of Convergence Knowledge
  • Publisher(Ko) :융복합지식학회
  • Journal Title :The Society of Convergence Knowledge Transactions
  • Journal Title(Ko) :융복합지식학회논문지
  • Volume : 12
  • No :1
  • Pages :77-88
  • DOI :https://doi.org/10.22716/sckt.2024.12.1.008
Journal Informaiton The Society of Convergence Knowledge Transactions The Society of Convergence Knowledge Transactions
Online Submission
  • NRF
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close