본문 바로가기
KERD
논문KCI 등재

트랜잭션 기반 추천 시스템에서 워드 임베딩을 통한 도메인 지식 반영

Application of Domain Knowledge in Transaction-based Recommender Systems through Word Embedding

문현실|조윤호|최영제
한국지식경영학회 (The Knowledge Management Society of Korea)|2020.03|지식경영연구 (Knowledge Management Research)|제21권 제1호|pp. 117-136|DOI 10.15813/kmr.2020.21.1.007

0

조회

0

다운로드

2

인용

0

참고문헌

키워드

SARTransaction-based recommender systemWord embeddingDomain knowledgeBook recommendation
주제분류경영학

초록

In the studies for the recommender systems which solve the information overload problem of users, the use of transactional data has been continuously tried. Especially, because the firms can easily obtain transactional data along with the development of IoT technologies, transaction-based recommender systems are recently used in various areas. However, the use of transactional data has limitations that it is hard to reflect domain knowledge and they do not directly show user preferences for individual items. Therefore, in this study, we propose a method applying the word embedding in the transaction-based recommender system to reflect preference differences among users and domain knowledge. Our approach is based on SAR, which shows high performance in the recommender systems, and we improved its components by using FastText, one of the word embedding techniques. Experimental results show that the reflection of domain knowledge and preference difference has a significant effect on the performance of recommender systems. Therefore, we expect our study to contribute to the improvement of the transaction-based recommender systems and to suggest the expansion of data used in the recommender system.

Abstract

In the studies for the recommender systems which solve the information overload problem of users, the use of transactional data has been continuously tried. Especially, because the firms can easily obtain transactional data along with the development of IoT technologies, transaction-based recommender systems are recently used in various areas. However, the use of transactional data has limitations that it is hard to reflect domain knowledge and they do not directly show user preferences for individual items. Therefore, in this study, we propose a method applying the word embedding in the transaction-based recommender system to reflect preference differences among users and domain knowledge. Our approach is based on SAR, which shows high performance in the recommender systems, and we improved its components by using FastText, one of the word embedding techniques. Experimental results show that the reflection of domain knowledge and preference difference has a significant effect on the performance of recommender systems. Therefore, we expect our study to contribute to the improvement of the transaction-based recommender systems and to suggest the expansion of data used in the recommender system.

참고문헌 (43)

  1. 김민정, "빅데이터 기반 추천시스템 구현을 위한 다중 프로파일 앙상블 기법", 지능정보연구, 21(4), pp.93~110 (2015), 한국지능정보시스템학회
  2. 박현정, "CNN을 적용한 한국어 상품평 감성분석: 형태소 임베딩을 중심으로", 지능정보연구, 24(2), pp.59~83 (2018), 한국지능정보시스템학회[DOI]
  3. 심재문, "상황인식 기술을 이용한 운전자 선호도 기반 교통상세정보 추천 시스템", 지식경영연구, 11(2), pp.75~93 (2010), 한국지식경영학회[DOI]
  4. 이재성, "RFM 다차원 분석 기법을 활용한 암시적 사용자 피드백 기반 협업 필터링 개선 연구", 지능정보연구, 25(1), pp.139~161 (2019), 한국지능정보시스템학회
  5. 이재영, "온라인 추천정보와 선호 유사성의 역할: 2단계 구매 의사 결정 모델을 중심으로", 지식경영연구, 16(3), pp.149~169 (2015), 한국지식경영학회[DOI]
  6. 정영진, "온라인 구매 행태를 고려한 토픽 모델링 기반 도서 추천", 지식경영연구, 18(4), pp.97~118 (2017), 한국지식경영학회[DOI]
  7. 조현수, "FastText를 적용한 한국어단어 임베딩", 한국정보과학회 2017 한국소프트웨어종합학술대회 논문집, pp.705~707 (2017)
  8. Barkan, O, "Item2vec: neural item embedding for collaborative filtering", 2016 IEEE 26th I nter nat iona l Work shop on Mach i ne Learning for Signal Processing, pp.1~6 (2016)
  9. Bojanowski, P, "Enriching word vectors with subword information", Transactions of the Association for Computational Linguistics, (5), pp.135~146 (2017)
  10. Breese, J. S, "Empirical analysis of predictive algorithms for collaborative filtering", Proceedings of the 14th Annual Conference on Uncertainty in Artificial Intelligence, pp.43~52 (1998)
  11. Brusilovsky, P, "Social information access: system sand technologies" (2018), Springer
  12. Gunawardana, A, "A survey of accuracy evaluation metrics of recommendation tasks", Journal of Machine Learning Research, (10), pp.2935~2962 (2009)
  13. Guo, G, "Resolving data sparsity by multi-type auxiliary implicit feedback for recommender systems", Knowledge-Based Systems, (138), pp.202~207 (2017)
  14. Hauc ap, J, "Google, Facebook, Amazon, eBay: Is the Internet driving competition or market monopolization?", International Economics and Economic Policy, 11(1), pp.49~61 (2014)
  15. Harper, F.M, "The movielens datasets: History and context", Acmtransactions on interactive intelligent systems, 5(4), pp.1~19 (2015)
  16. Herlocker, J. L., "Evaluating collaborative f iltering recommender systems", ACM Transactions on Information Systems, 22(1), pp.5~53 (2004)
  17. He, X, "Neural collaborative f iltering", Proceedings of t he 26t h international conference on world wide web, pp.173~182 (2017)
  18. He, X, "Fast matrix factorization for online recommendation with implicit feedback", Proceedings o f t he 3 9th I nternational ACM SIGIR conference on Research and Development in Information Retrieval, pp.549~558 (2016)
  19. Hsu, C.N, "Mining skewed and sparse transaction data for personalized shopping recommendation", Machine Learning, 57(1-2), pp.35~59 (2004)
  20. Konstan, J. A, "GroupLens: applying collaborative filtering to usenet news", Communications of the ACM, 40(3), pp.77~87 (1997)
  21. 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, pp.426~434 (2008)
  22. Lathia, N, "Temporal diversity in recommender systems", Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval, pp.210~217 (2010)
  23. Lee, S.K, "Collaborative filtering with ordinal scalebased implicit ratings for mobile music recommendations", Information Sciences, 180(11), pp.2142~2155 (2010)
  24. Lee, T.Q, "A timebased approach to effective recommender systems using implicit feedback", Expert systems with applications, 34(4), pp.3055~3062 (2008)
  25. Lee, T.Q, "An empirical study on effectiveness of temporal information as implicit ratings", Expert systems with Applications, 36(2), pp.1315~1321 (2009)
  26. Levy, O, "Advances inneural information processing systems", pp.2177~2185 (2014)
  27. Liu, M, "Mixed similarity learning for recommendation with implicit feedback", Knowledge-Based Systems, (119), pp.178~185 (2017)
  28. Mikolov, T, "Advances in neural information processing systems", pp.3111~3119 (2013)
  29. Mnih, A, "Advances in neural information processing systems", pp.1257~1264 (2008)
  30. Mooney, R.J, "Content-based book recommending using learning for text categorization", Proceedings of the fifth ACM conference on Digital libraries, pp.195~204 (2000)
  31. Oard, D.W, "Implicit Feedback for Recommender Systems", Proceedings of the 5th DELOS Workshop on Filtering and Collaborative Filtering, pp.31~36 (1998)
  32. Parra, D, "Walk the talk", International Conference on User Modeling, Adaptation, and Personalization, pp.255~268 (2011)
  33. Persson, P, "“Attention manipulation and information overload", Behavioural Public Policy, 2(1), pp.78~106 (2018)
  34. Resn ick, P, "GroupLens: An open architecture for collaborative filtering of netnews", Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work, pp.175~186 (1994)
  35. Sarwar, B, "Item-based collaborative filtering recommendation algorithms", Proceedings of the 10th International Conference on World Wide Web, pp.285~295 (2001)
  36. Schafer, J.B, "The adaptive web", pp.291~324 (2007), Springer
  37. Sikka, K, "Exploring bag of words architectures in the facial expression domain", European Conference on Computer Vision, pp.250~259 (2012)
  38. Terveen, L, "PHOAKS: a system for sharing recommendations", Communications of the ACM, 40(3), pp.59~62 (1997)
  39. Tewari, A.S, "Book recommendation system based on combine features of content based filtering, collaborative filtering and association rule mining", 2014 IEEE International Advance Computing Conference, pp.500~503 (2014)
  40. Wallach, H. M, "Topic modeling: beyond bag-of-words", Proceedings of the 23rd international conference on Machine learning, pp.977~984 (2006)
  41. Wu, L, "Semantics-preserving bag-of-words models and applications", IEEE Transactions on Image Processing, 19(7), pp.1908~1920 (2010)
  42. Yu, T, "Incremental learning formatrix factorization in recommender systems", 2016 I EEE International Conference on Big Data, pp.1056~1063 (2016)
  43. Zhou, Y, "Large-scale parallel collaborative filtering for the netflix prize", International conference on algorithmic applications in management, pp.337~348 (2008), Springer

관련 논문AI추천

새로운 사용자 문제 개선을 위한 워드임베딩 학습과 Skip-gram 모델링 기반의 추천 시스템김경창, 신수미한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2016 · 제21권 제7호다중 분류 기반의 상품 추천을 위한 워드 임베딩 적용 연구김철진한국지식정보기술학회 · 한국지식정보기술학회 논문지2022 · 제17권 제1호고객의 검색패턴과 상품 상세정보를 활용한 상품 추천 모형의 개선안현철, 이윤주, 이재준한국컴퓨터정보학회 · 한국컴퓨터정보학회논문지2021 · 제26권 제1호Word2Vec을 이용한 사용자기반 협업필터링의 예측 정확도 개선강부식한국지식정보기술학회 · 한국지식정보기술학회 논문지2018 · 제13권 제1호Word2Vec과 심층 신경망을 활용한 영화추천 시스템의 정확도 개선강부식한국지식정보기술학회 · 한국지식정보기술학회 논문지2018 · 제13권 제5호온라인 구매 행태를 고려한 토픽 모델링 기반 도서 추천정영진, 조윤호한국지식경영학회 · 지식경영연구2017 · 제18권 제4호

이 간행물의 다른 논문 (10건)

특허분쟁이 기업의 향후 혁신 활동에 미치는 영향이종선, 김나미pp. 1-25다중반응표면 최적화를 위한 단변량 손실함수법: 대화식 절차 기반의 가중치 결정정인준pp. 27-404차산업혁명 핵심기술 도입 및 정보보호조직에 관한 탐색적 연구: 성과측면에서의 비교분석조혜진, 임소희, 김기현pp. 41-59디지털뱅킹 플랫폼 기반 핀테크 사례 연구: 코스콤정이철, 이상기, 김희웅pp. 61-78최고 경영자의 인구통계학적 특성이 조직 디커플링 행위에 미치는 영향김용, 최영준pp. 79-98
원문 보기