Journal of Fashion Business (패션비즈니스)

The Korean Society of Fashion Business (한국패션비즈니스학회)
권호 표지
DOI QR코드

DOI QR Code

Proposal for User-Product Attributes to Enhance Chatbot-Based Personalized Fashion Recommendation Service

챗봇 기반의 개인화 패션 추천 서비스 향상을 위한 사용자-제품 속성 제안

  • 안효선 (이화여자대학교, 의류산업학과) ;
  • 김성훈 ((주)에이아이닷엠) ;
  • 최예림 (서울여자대학교, 데이터사이언스학과)
  • Received : 2023.05.15
  • Accepted : 2023.06.13
  • Published : 2023.07.30
Download PDF
⟨ Previous Next ⟩

Abstract

The e-commerce fashion market has experienced a remarkable growth, leading to an overwhelming availability of shared information and numerous choices for users. In light of this, chatbots have emerged as a promising technological solution to enhance personalized services in this context. This study aimed to develop user-product attributes for a chatbot-based personalized fashion recommendation service using big data text mining techniques. To accomplish this, over one million consumer reviews from Coupang, an e-commerce platform, were collected and analyzed using frequency analyses to identify the upper-level attributes of users and products. Attribute terms were then assigned to each user-product attribute, including user body shape (body proportion, BMI), user needs (functional, expressive, aesthetic), user TPO (time, place, occasion), product design elements (fit, color, material, detail), product size (label, measurement), and product care (laundry, maintenance). The classification of user-product attributes was found to be applicable to the knowledge graph of the Conversational Path Reasoning model. A testing environment was established to evaluate the usefulness of attributes based on real e-commerce users and purchased product information. This study is significant in proposing a new research methodology in the field of Fashion Informatics for constructing the knowledge base of a chatbot based on text mining analysis. The proposed research methodology is expected to enhance fashion technology and improve personalized fashion recommendation service and user experience with a chatbot in the e-commerce market.

Keywords

Acknowledgement

본 연구는 문화체육관광부 및 한국콘텐츠진흥원의 2023년도 문화기술 연구개발 사업으로 수행되었음 (과제명: 패션과 스타일테크 융합 메타버스 이커머스 플랫폼 기술개발,과제번호:RS-2023-00220957)

References

  1. Acumen Research and Consulting. (2022). Chatbot market analysis global industry size, share, trends and forecast 2022-2030. Retrieved June 15, 2023, from https://www.acumenresearchandconsulting.com/chatbot-market
  2. An, H., Kwon, S., & Park, M. (2019). A case study on the recommendation services for customized fashion styles based on artificial intelligence. Journal of the Korean Society of Clothing and Textiles, 43(3), 349-360. doi:10.5850/JKSCT.2019.43.3.349
  3. An, H., Lee, K. Y., Choi, Y., & Park, M. (2023). Conceptual framework of hybrid style in fashion image datasets for machine learning. Fashion and Textiles, 10(1), 1-18. doi:10.1186/s40691-023-00338-8
  4. Choi, Y. S., & Choy, H. S. (2007). A study on the fashion styling for personal image making. Fashion & Textile Research Journal, 9(1), 49-54.
  5. Chung, M., Ko, E., Joung, H., & Kim, S. J. (2020). Chatbot e-service and customer satisfaction regarding luxury brands. Journal of Business Research, 117, 587-595. doi:10.1016/j.jbusres.2018.10.004
  6. Cuthbertson, A. (2022, December 2). 'Google is done': world's most powerful AI chatbot offers human-like alternative to search engines. Independent. Retrieved June 15, 2023, from https://www.independent.co.uk/tech/ai-chatbot-chatgpt-google-openai-b2237834.html
  7. Dahunsi, B. O., & Dunne, L. E. (2021). Understanding professional fashion stylists' outfit recommendation process: A qualitative study. Recommender Systems in Fashion and Retail (pp. 139-160). Cham, Switzerland: Springer International Publishing. doi:10.1007/978-3-030-66103-8_8
  8. de Barros Costa, E., Rocha, H. J. B., Silva, E. T., Lima, N. C., & Cavalcanti, J. (2017). Understanding and personalising clothing recommendation for women. Recent Advances in Information Systems and Technologies (pp. 841-850). Cham, Switzerland: Springer International Publishing. doi:10.1007/978-3-319-56535-4_82
  9. Dong, M., Zeng, X., Koehl, L., & Zhang, J. (2020). An interactive knowledge-based recommender system for fashion product design in the big data environment. Information Sciences, 540, 469-488. doi:10.1016/j.ins.2020.05.094
  10. Han, S. J., & Kim, I. Y. (2016). Fashion Design. Seoul: Kyohakyongusa.
  11. Han, S. J., Yang, L. N., & Kim, M. S. (2002). A study on the clothing buying motive and information source according to lifestyle type of women in their 50's and 60's. The Research Journal of the Costume Culture, 10(2), 116-131.
  12. Hoegg, J., Scott, M. L., Morales, A. C., & Dahl, D. W. (2014). The flip side of vanity sizing: How consumers respond to and compensate for larger than expected clothing sizes. Journal of Consumer Psychology, 24(1), 70-78. doi:10.1016/j.jcps.2013.07.003
  13. Husak, V., Lozynska, O., Karpov, I., Peleshchak, I., Chyrun, S., & Vysotskyi, A. (2020). Information system for recommendation list formation of clothes style image selection according to user's needs based on NLP and Chatbots. 4th International Conference On Computational Linguistics And Intelligent Systems (pp. 788-818). Lviv, Ukraine: Sun SITE Central Europe.
  14. Hyun, Y. G., Lim, J. T., Han, J. H., Chae, U., Lee, G. H., Ko, J. D., Cho, Y. H., & Lee, J. Y. (2020). A study on the development methodology for user-friendly interactive chatbot. Journal of Digital Convergence, 18(11), 215-226. doi:10.14400/JDC.2020.18.11.215
  15. Jackson, C. (1980). Color me beautiful: Discover your natural beauty through the colors that make you look great and feel fabulous. Washington, D.C.: Acropolis Books Ltd.
  16. Jang, D. S., & Chun, J. H. (2007). Automated classification scheme generation using product attribute information. The KIPS Transactions: PartD, 14(5), 491-500. doi:10.3745/KIPSTD.2007.14.5.491
  17. Jannach, D., Manzoor, A., Cai, W., & Chen, L. (2021). A survey on conversational recommender systems. ACM Computing Surveys(CSUR), 54(5), 1-36. doi:10.1145/3453154
  18. Ji, S., Pan, S., Cambria, E., Marttinen, P., & Philip, S. Y. (2021). A survey on knowledge graphs: Representation, acquisition, and applications. IEEE transactions on neural networks and learning systems, 33(2), 494-514. doi:10.1109/TNNLS.2021.3070843
  19. Jung, Y. S. (2021). A study on the quantitative diagnosis model of personal color. Journal of Convergence for Information Technology, 11(11), 277-287. doi:10.22156/CS4SMB.2021.11.11.277
  20. Kang, W. C., Fang, C., Wang, Z., & McAuley, J. (2017). Visually-aware fashion recommendation and design with generative image models. 2017 IEEE international conference on data mining (ICDM) (pp. 207-216). New Orleans, LA: IEEE. doi:10.1109/ICDM.2017.30
  21. Kim, H., & Choi, Y. M. (2022). A case study of fashion style in accordance with TPO of K-virtual influencer. International Textile and Apparel Association Annual Conference Proceedings (Vol. 78, No. 1). Virtual: Iowa State University Digital Press. doi:10.31274/itaa.13593
  22. Kim, S., Son, Y., Kim, S., Kang, Y., Seo, H., Kim, M., & Choi, Y. (2022). Incremental learning framework of knowledge graph based on user preference for conversational recommender system. Proceedings of the Korean Institute of Information Scientists and Engineers Conference, (pp. 1208-1210). Seoul: Korean Institute of Information Scientist and Engineers.
  23. Kwon, H. S., Hwang, S. J., Kwon, H. W., & Kim, Y. (2013). 패션과 이미지메이킹 [Fashion and Image Making]. Seoul: Soohaksa. pp. 56-58.
  24. Lamb, J. M., & Kallal, M. J. (1992). A conceptual framework for apparel design. Clothing and Textiles Research Journal, 10(2), 42-47. doi:10.1177/0887302X9201000207
  25. Landim, A. R. D. B., Pereira, A. M., Vieira, T., de B. Costa, E., Moura, J. A. B., Wanick, V., & Bazaki, E. (2022). Chatbot design approaches for fashion E-commerce: An interdisciplinary review. International Journal of Fashion Design, Technology and Education, 15(2), 200-210. doi:10.1080/17543266.2021.1990417
  26. Lee, J. (2020). A study on the design of a fashion curation service for customized styling of middle-aged women. (Unpublished doctoral dissertation), Ewha Womans University, Seoul, Korea.
  27. Lee, K. S., Kim, H. S., & Park, Y. S. (2011). 패션 스타일링을 위한 코디네이션 [Coordination for a fashion styling]. Paju: Gyomoonsa.
  28. Lee, Y. H. (2004). The meaning of personal color in the view of total coordination. Journal of the Korean Society of Fashion and Beauty, 2(1), 1-4.
  29. Lee, Y., Kim, H., & Park, M. (2022). The effects of perceived quality of fashion chatbot's product recommendation service on perceived usefulness, trust and consumer response. Journal of the Korean Society of Clothing and Textiles, 46(1), 80-98. doi:10.5850/JKSCT.2022.46.1.80
  30. Olufisayo Dahunsi, B. (2021). An ontology-based knowledgebase for user profile and garment features in apparel recommender systems. Proceedings of the 15th ACM Conference on Recommender Systems (pp. 851-854). Amsterdam, Netherlands: Association for Computing Machinery. doi:10.1145/3460231.3473901
  31. Orzada, B. T., & Kallal, M. J. (2021). FEA consumer needs model: 25 years later. Clothing and Textiles Research Journal, 39(1), 24-38. doi:10.1177/0887302X19881211
  32. Park, E. J., & Rhee, E. (1995). A typology of apparel usage situations among female consumers. Journal of the Korean Society of Clothing and Textiles, 19(5), 713-722.
  33. Park, J. H., & Suh, M. A. (2006). A study of preference about wedding dress design according to body shape for adult women. The Research Journal of the Costume Culture, 14(4), 625-634.
  34. Ray, S. (2023, February 22). JP morgan chase restricts staffers' use of ChatGPT. Forbes. Retrieved June 15, 2023, from https://www.forbes.com/sites/siladityaray/2023/02/22/jpmorgan-chase-restricts-staffers-use-of-chatgpt/?sh=780781746bc7
  35. Shawar, B. A., & Atwell, E. (2007). Chatbots: are they really useful?. Journal for Language Technology and Computational Linguistics, 22(1), 29-49. doi:10.21248/jlcl.22.2007.88
  36. Taecharungroj, V. (2023). "What can chatGPT do?" analyzing early reactions to the innovative AI chatbot on twitter. Big Data and Cognitive Computing, 7(1), 35. doi:10.3390/bdcc7010035
  37. Tan, S. M., & Liew, T. W. (2020). Designing embodied virtual agents as product specialists in a multiproduct category E-commerce: The roles of source credibility and social presence. International Journal of Human-Computer Interaction, 36(12), 1136-1149. doi:10.1080/10447318.2020.1722399
  38. Wang, X, & Ryoo, S. (2009). Wedding dress preference according to body shape in female college students. Scientific Journal, 35, 63-76.
  39. Yoon, H. Y., Choi, S. K., & Jeong, S. J. (2012). A study on the online clothing purchasing behavior characteristics of adolescents. Journal of the Korean Society of Design Culture, 18(3), 297-308.
  40. Yoon, M. K., & Jang, A. H. (2018). Fashion Styling. Seoul: Soohaksa.
  41. Zalmout, N., Zhang, C., Li, X., Liang, Y., & Dong, X. L. (2021). All you need to know to build a product knowledge graph. Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (pp. 4090-4091). Singapore: Association for Computing Machinery. doi:10.1145/3447548.3470825