DOI QR코드

DOI QR Code

A Study on the Development and Evaluation of Personalized Book Recommendation Systems in University Libraries Based on Individual Loan Records

대출 기록에 기초한 대학 도서관 도서 개인화 추천시스템 개발 및 평가에 관한 연구

  • 홍연경 (성균관대학교 문헌정보학과) ;
  • 전서영 (성균관대학교 문헌정보학과) ;
  • 최재영 (성균관대학교 문헌정보학과) ;
  • 양희윤 (성균관대학교 문헌정보학과) ;
  • 한채은 (성균관대학교 문헌정보학과) ;
  • 주영준 (성균관대학교 문헌정보학과)
  • Received : 2021.05.17
  • Accepted : 2021.06.12
  • Published : 2021.06.30

Abstract

The purpose of this study is to propose a personalized book recommendation system to promote the use of university libraries. In particular, unlike many recommended services that are based on existing users' preferences, this study proposes a method that derive evaluation metrics using individual users' book rental history and tendencies, which can be an effective alternative when users' preferences are not available. This study suggests models using two matrix decomposition methods: Singular Value Decomposition(SVD) and Stochastic Gradient Descent(SGD) that recommend books to users in a way that yields an expected preference score for books that have not yet been read by them. In addition, the model was implemented using a user-based collaborative filtering algorithm by referring to book rental history of other users that have high similarities with the target user. Finally, user evaluation was conducted for the three models using the derived evaluation metrics. Each of the three models recommended five books to users who can either accept or reject the recommendations as the way to evaluate the models.

본 연구는 대학 도서관 사용 증진을 위하여 개인별 맞춤 도서 추천시스템을 구축하는 것을 목적으로 한다. 특히 사용자의 아이템에 대한 선호도가 존재하는 다수의 추천시스템과는 달리, 선호도가 존재하지 않을 때에 도서 추천이 가능하도록 하는 방안인 도서관 이용자의 도서 대출 목록과 성향을 활용하여 평가지표를 생성하는 방법을 제안하고자 한다. 이용자가 아직 읽지 않은 책에 대한 예상 선호도를 산출하는 방식으로 도서를 추천하는 행렬 분해 방법인 Singular Value Decomposition(SVD)과 Stochastic Gradient Descent(SGD) 알고리즘을 활용한 모델을 구축했다. 더불어 유사도가 높은 이용자 그룹 내의 도서 대출 목록을 참조하여 추천하는 사용자 기반 협업 필터링 알고리즘을 활용해 모델을 구현했다. 최종적으로 평가지표를 활용한 세 가지 모델에 대하여 사용자 평가를 진행했다. 각각의 모델이 제시한 개인별 맞춤 도서 다섯 권의 목록을 해당 대출자에게 제공하고, 추천 도서에 대한 만족/불만족 여부를 이진화 점수화하여 모델에 대한 평가를 진행했다.

Keywords

References

  1. Cho, Yeon Sun (2019). A study on the effect of collaborative filtering recommendation system on the use of school library, Yonsei University, Korea.
  2. Chung, Hee Chung & Cho, Sung-Bae (2011). Personalized recommendation service based on collaborative filtering for library information system. Communications of the Korean Institute of Information Scientists and Engineers, 38(1A), 251-254.
  3. Jeong, Seung-Yoon (2017). A recommender system using factorization machine. Journal of Digital Contents Society, 18(4), 707-712. http://doi.org/10.9728/dcs.2017.18.4.707
  4. Noh, Younghee (2014). A study suggesting the development direction of the next generation digital library. Journal of Korean Society for Information Management, 31(2), 7-40. https://doi.org/10.3743/KOSIM.2014.31.2.007
  5. Oh, Seung Sun (2015). A study on personal book recommendation service by SNS Analysis: Focus on Twitter, Yonsei University, Korea.
  6. Park, Yang-Ha (2016). A study on the book recommendation standards of book-curation service for school library. Journal of Korean Library and Information Science Society, 47(1), 279-303. http://doi.org/10.16981/kliss.47.1.201603.279
  7. Herlovker, J., Konstans, J., Terveen, L., & Riedl, J. (2004). Evaluating Collaborative Filtering Recommender Systems. ACM Transactions on Information Systems, 22(1), 5-53. https://doi.org/10.1145/963770.963772
  8. Hu, Y., Koren, Y., & Volinsky, C. (2008). Collaborative Filtering for Implicit Feedback Datasets, 2008 Eighth IEEE International Conference on Data Mining, 263-272. https://doi.org/10.1109/ICDM.2008.22
  9. Kanetkar, S., Nayak, A., Swamy, S., & Bhatia, G. (2014). Web-based personalized hybrid book recommendation system, 2014 International Conference on Advances in Engineering & Technology Research (ICAETR - 2014), 1-5. https://doi.org/10.1109/ICAETR.2014.7012952
  10. Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix Factorization Techniques for Recommender Systems, Computer, 42(8), 30-37. https://doi.org/10.1109/MC.2009.263
  11. Linden, G., Smith, B., & York, J. (2003). Amazon.com recommendations: item-to-item collaborative filtering. IEEE Internet Computing, 7(1), 76-80. https://doi.org/10.1109/MIC.2003.1167344
  12. SNU NOW (2019. 09. 30). 중앙도서관, 맞춤형 도서 추천 서비스 제공. 출처: https://now.snu.ac.kr/47/2/1438
  13. Tsuji, K., Takizawa, N., Sato, S., Ikeuchi, U., Ikeuchi, A., Yoshikane, F., & Itsumura, H. (2014). Book Recommendation Based on Library Loan Records and Bibliographic Information. Procedia-social and behavioral sciences, 147, 478-486. https://doi.org/10.1016/j.sbspro.2014.07.142
  14. Tsuji, K., Yoshikane, F., Sato, S., & Itsumura, H. (2014). Book Recommendation Using Machine Learning Methods Based on Library Loan Records and Bibliographic Information. 2014 IIAI 3rd International Conference on Advanced Applied Informatics, 76-79. https://doi.org/10.1109/IIAI-AAI.2014.26