Journal of Information Technology Services (한국IT서비스학회지)

Korea Society of IT Services (한국IT서비스학회)
권호 표지
DOI QR코드

DOI QR Code

Developing a Graph Convolutional Network-based Recommender System Using Explicit and Implicit Feedback

명시적 및 암시적 피드백을 활용한 그래프 컨볼루션 네트워크 기반 추천 시스템 개발

  • 이흠철 (경희대학교 대학원 빅데이터응용학과) ;
  • 김동언 (경희대학교 대학원 빅데이터응용학과) ;
  • 이청용 (경희대학교 대학원 빅데이터응용학과) ;
  • 김재경 (경희대학교 경영대학/빅데이터응용학과)
  • Received : 2023.01.13
  • Accepted : 2023.02.21
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

With the development of the e-commerce market, various types of products continue to be released. However, customers face an information overload problem in purchasing decision-making. Therefore, personalized recommendations have become an essential service in providing personalized products to customers. Recently, many studies on GCN-based recommender systems have been actively conducted. Such a methodology can address the limitation in disabling to effectively reflect the interaction between customer and product in the embedding process. However, previous studies mainly use implicit feedback data to conduct experiments. Although implicit feedback data improves the data scarcity problem, it cannot represent customers' preferences for specific products. Therefore, this study proposed a novel model combining explicit and implicit feedback to address such a limitation. This study treats the average ratings of customers and products as the features of customers and products and converts them into a high-dimensional feature vector. Then, this study combines ID embedding vectors and feature vectors in the embedding layer to learn the customer-product interaction effectively. To evaluate recommendation performance, this study used the MovieLens dataset to conduct various experiments. Experimental results showed the proposed model outperforms the state-of-the-art. Therefore, the proposed model in this study can provide an enhanced recommendation service for customers to address the information overload problem.

Keywords

Acknowledgement

본 논문은 교육부 및 한국연구재단 4단계 두뇌한국21 사업(4단계 BK21 사업)으로부터 지원받은 연구임.

References

  1. 김동언, 김민지, 김재경, "소규모 전자상거래를 위한 추천 시스템의 시간 차이에 따른 추천 효과 측정에 관한 연구", 인터넷전자상거래연구, 제22권, 제6호, 2022, 185-202. https://doi.org/10.37272/JIECR.2022.12.22.6.185
  2. 김재경, 오희영, 권오병, "유비쿼터스 환경에서 연관규칙과 협업필터링을 이용한 상품그룹추천", 한국 IT서비스학회지, 제6권, 제2호, 2007, 113-123.
  3. 권혁인, 나윤빈, 유미옥, 최광선, "도서정보 기반의 고객 맞춤형 큐레이션 서비스 및 비즈니스 모델 연구", 한국IT서비스학회지, 제14권, 제1호, 2015, 251-262. https://doi.org/10.9716/KITS.2015.14.1.251
  4. 이청용, 전상홍, 이창재, 김재경, "사용자의 선호도 정보를 활용한 직무 추천 시스템 연구", 한국IT서비스학회지, 제20권, 제3호, 2021, 57-73. https://doi.org/10.9716/KITS.2021.20.3.057
  5. 이흠철, 윤효림, 이청용, 김재경, "Multi-channel CNN 기반 온라인 리뷰 유용성 예측 모델 개발에 관한 연구", 지능정보연구, 제28권, 제2호, 2022, 171-189. https://doi.org/10.13088/JIIS.2022.28.2.171
  6. 홍태호, 홍준우, 김은미, 김민수, "영화 리뷰의 상품 속성과 고객 속성을 통합한 지능형 추천시스템", 지능정보연구, 제28권, 제2호, 2022, 1-18. https://doi.org/10.13088/JIIS.2022.28.2.001
  7. Abdollahpouri, H., G. Adomavicius, R. Burke, I. Guy, D. Jannach, T. Kamishima, J. Krasnodebski, and L. Pizzato, "Multistakeholder recommendation: Survey and research directions", User Modeling and User-Adapted Interaction, Vol.30, No.1, 2020, 127-158. https://doi.org/10.1007/s11257-019-09256-1
  8. Al-Bakri, N.F. and S.H. Hashim, "Reducing data sparsity in recommender systems", Al-Nahrain Journal of Science, Vol.21, No.2, 2018, 138-147. https://doi.org/10.22401/JNUS.21.2.20
  9. Bennett, J. and S. Lanning, "The netflix prize", Proceedings of KDD Cup and Workshop 2007, San Jose, USA, 2007, 35-38.
  10. Berg, R.V.D., T.N. Kipf, and M. Welling, "Graph convolutional matrix completion", arXiv preprint arXiv:1706.02263, 2017.
  11. Chen, S. and Y. Peng, "Matrix factorization for recommendation with explicit and implicit feedback", Knowledge-Based Systems, Vol.158, 2018, 109-117. https://doi.org/10.1016/j.knosys.2018.05.040
  12. Das, A.S., M. Datar, A. Garg, and S. Rajaram, "Google news personalization: scalable online collaborative filtering", Proceedings of the 16th International Conference on World Wide Web, Banff, Canada, 2007, 271-280.
  13. Dogan, O., F.C. Kem, and B. Oztaysi, "Fuzzy association rule mining approach to identify e-commerce product association considering sales amount", Complex & Intelligent Systems, Vol.8, No.2, 2022, 1551-1560. https://doi.org/10.1007/s40747-021-00607-3
  14. Goldberg, D., D. Nichols, B.M. Oki, and D. Terry, "Using collaborative filtering to weave an information tapestry", Communications of the ACM, Vol.35, No.12, 1992, 61-70. https://doi.org/10.1145/138859.138867
  15. Harper, F.M. and J.A. Konstan, "The movielens datasets: History and context", ACM Transactions on Interactive Intelligent Systems, Vol.5, No.4, 2015, 1-19. https://doi.org/10.1145/2827872
  16. He, X., K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang, "Lightgcn: Simplifying and powering graph convolution network for recommendation", Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Xi'an, China, 2020, 639-648.
  17. He, X., L. Liao, H. Zhang, L. Nie, X. Hu, and T.S. Chua, "Neural collaborative filtering", Proceedings of the 26th International Conference on World Wide Web, Perth, Australia, 2017, 173-182.
  18. Huang, T., Y. Dong, M. Ding, Z. Yang, W. Feng, X. Wang, and J. Tang, "Mixgcf: An improved training method for graph neural network-based recommender systems", Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, Singapore, 2021, 665-674.
  19. Idrissi, N. and A. Zellou, "A systematic literature review of sparsity issues in recommender systems", Social Network Analysis and Mining, Vol.10, No.1, 2020, 1-23. https://doi.org/10.1007/s13278-019-0612-8
  20. Kim, J.K., H.K. Kim, H.Y. Oh, and Y.U. Ryu, "A group recommendation system for online communities", International Journal of Information Management, Vol.30, No.3, 2010, 212-219. https://doi.org/10.1016/j.ijinfomgt.2009.09.006
  21. Kipf, T.N. and M. Welling, "Semi-supervised classification with graph convolutional networks", arXiv preprint arXiv:1609.02907, 2016.
  22. Koren, Y., "Factorization meets the neighborhood: a multifaceted collaborative filtering model", Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Las Vegas, USA, 2008, 426-434.
  23. Koren, Y., R. Bell, and C. Volinsky, "Matrix factorization techniques for recommender systems", Computer, Vol.42, No.8, 2009, 30-37. https://doi.org/10.1109/MC.2009.263
  24. Lee, D. and K. Hosanagar, "How do recommender systems affect sales diversity? A cross-category investigation via randomized field experiment", Information Systems Research, Vol.30, No.1, 2019, 239-259. https://doi.org/10.1287/isre.2018.0800
  25. Lima, G.R., C.E. Mello, A. Lyra, and G. Zimbrao, "Applying landmarks to enhance memorybased collaborative filtering", Information Sciences, Vol.513, 2020, 412-428. https://doi.org/10.1016/j.ins.2019.10.041
  26. Nilashi, M., O. Ibrahim, and K. Bagherifard, "A recommender system based on collaborative filtering using ontology and dimensionality reduction techniques", Expert Systems with Applications, Vol.92, 2018, 507-520. https://doi.org/10.1016/j.eswa.2017.09.058
  27. Park, S. and J.L. Nicolau, "Asymmetric effects of online consumer reviews", Annals of Tourism Research, Vol.50, 2015, 67-83. https://doi.org/10.1016/j.annals.2014.10.007
  28. Rendle, S., C. Freudenthaler, Z. Gantner, and L.S. Thieme, "BPR: Bayesian personalized ranking from implicit feedback", arXiv preprint arXiv:1205.2618, 2012.
  29. Renjith, S., A. Sreekumar, and M. Jathavedan, "An extensive study on the evolution of context-aware personalized travel recommender systems", Information Processing & Management, Vol.57, No.1, 2020, 102078.
  30. Resnick, P., N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, "Grouplens: An open architecture for collaborative filtering of netnews", Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work, Chapel Hill, USA, 1994, 175-186.
  31. Sarwar, B., G. Karypis, J. Konstan, and J. Riedl, "Item-based collaborative filtering recommendation algorithms", Proceedings of the 10th International Conference on World Wide Web, Hong Kong, 2001, 285-295.
  32. Schafer, J.B., D. Frankowski, J. Herlocker, and S. Sen, "Collaborative filtering recommender systems", The Adaptive Web, Springer, New York, 2007.
  33. Singh, M., "Scalability and sparsity issues in recommender datasets: A survey", Knowledge and Information Systems, Vol.62, No.1, 2020, 1-43. https://doi.org/10.1007/s10115-018-1254-2
  34. Su, X. and T.M. Khoshgoftaar, "A survey of collaborative filtering techniques", Advances in Artificial Intelligence, Vol.2009, No.4, 2009, 1-19.
  35. Tang, H., W. Yang, and S. Zheng, "Intelligent information recommendation algorithm under background of big data land cultivation", Microprocessors and Microsystems, Vol.81, 2021, 103728.
  36. Tay, Y., L.A. Tuan, and S.C. Hui, "Latent relational metric learning via memory-based attention for collaborative ranking", Proceedings of the 2018 World Wide Web Conference, Lyon, France, 2018, 729-739.
  37. Wang, H., N. Wang, and D.Y. Yeung, "Collaborative deep learning for recommender systems", Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Sydney, Australia, 2015, 1235-1244.
  38. Wang, X., X. He, M. Wang, F. Feng, and T.S. Chua, "Neural graph collaborative filtering", Proceedings of the 42nd international ACM SIGIR Conference on Research and Development in Information Retrieval, Paris, France, 2019, 165-174.
  39. Xue, H.J., X. Dai, J. Zhang, S. Huang, and J. Chen, "Deep matrix factorization models for recommender systems", Proceedings of the 26th International Joint Conference on Artificial Intelligence, Melbourne, Australia, 2017, 3203-3209.
  40. Yao, Q., X. Chen, J.T. Kwok, Y. Li, and C.J. Hsieh, "Efficient neural interaction function search for collaborative filtering", Proceedings of The Web Conference 2020, Taipei, Taiwan, 2020, 1660-1670.
  41. Ying, R., R. He, K. Chen, P. Eksombatchai, W.L. Hamilton, and J. Leskovec, "Graph convolutional neural networks for web-scale recommender systems", Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK, 2018, 974-983.
  42. Yue, W., Z. Wang, W. Liu, B. Tian, S. Lauria, and X. Liu, "An optimally weighted user-and item-based collaborative filtering approach to predicting baseline data for Friedreich's Ataxia patients", Neurocomputing, Vol.419, 2021, 287-294. https://doi.org/10.1016/j.neucom.2020.08.031
  43. Zou, L., L. Xia, Y. Gu, X. Zhao, W. Liu, J.X. Huang and D. Yin, "Neural interactive collaborative filtering", Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Xi'an, China, 2020, 749-758.