The Journal of Society for e-Business Studies (한국전자거래학회지)

Society for e-Business Studies (한국전자거래학회)
권호 표지

Collaborative Tag-Based Recommendation Methods Using the Principle of Latent Factor Models

잠재 요인 모델의 원리를 이용한 협업 태그 기반 추천 방법

  • 김형도 (한양사이버대학교 경영학부)
  • Published : 2009.11.30
Download PDF
⟨ Previous Next ⟩

Abstract

Collaborative tagging systems allow users to attach tags to diverse sharable contents in social networks. These tags provide usefulness in reusing the contents for all community members as well as their creators. Three-dimensional data composed of users, items, and tags are used in the collaborative tag-based recommendation. They are generally more voluminous and sparse than two-dimensional data composed of users and items. Therefore, there are many difficulties in applying existing collaborative filtering methods directly to them. Latent factor models, which are also successful in the area of collaborative filtering recently, discover latent features(factors) for explaining observed values and solve problems based on the features. However, establishing the models require much time and efforts. In order to apply the latent factor models to three-dimensional collaborative filtering data, we have to overcome the difficulty of establishing them. This paper proposes various methods for determining preferences of users to items via establishing an intuitive model by assuming tags used for items as latent factors to users and items respectively. They are compared using real data for concluding desirable directions.

협업에 의한 태그 작성 시스템은 소셜 네트워크에서 다양한 공유 콘텐츠에 사용자가 태그를 부착할 수 있도록 허용하는데, 이러한 태그들은 본인뿐만 아니라 모든 커뮤니티 사용자들이 콘텐츠를 이용하는데 유용함을 준다. 협업 태그 기반의 추천에서는 사용자와 항목, 그리고 태그로 이루어진 3차원 데이터를 이용하는데, 이 데이터는 일반적으로 사용자와 항목으로 이루어진 2차원 데이터에 비하여 더 방대한 반면, 희소성(Sparsity)이 더 높다. 따라서 기존의 협업 필터링 기법을 바로 적용하는데 어려움이 많다. 잠재 요인 모델(Latent Factor Model)은 관찰된 값을 설명하는 잠재된 특징(요인)들을 밝히고, 이를 이용해서 문제를 해결하기 위한 모델로서 최근 협업 필터링에서도 성공적으로 적용되고 있으나, 모델을 학습하거나 개선하는 단계에서는 많은 시간과 노력이 필요하다는 단점이 있다. 이러한 잠재 요인 모델을 3차원 협업 태그 데이터에 적용하기 위해서는, 계산이 복잡한 협업 필터링 모델 수립의 어려움을 극복해야 한다. 이 논문에서는 사용자가 항목에 대해 사용한 태그들을 사용자 및 항목에 대한 잠재요인으로 간주하여 직관적인 모델을 수립하고, 사용자의 아이템에 대한 선호도를 결정하는 여러 가지 방법들을 제안하고, 실제 협업 태그 데이터를 이용하여 이들을 비교 평가한다.

Keywords

References

  1. 김형도, "일관성 기반의 신뢰도 정의에 의한 협업 필터링", 한국전자거래학회지, 제14권, 제1호, 2009, pp. 1-11.
  2. Ahn, H. J., "A New Similarity Measure for Collaborative Filtering to Alleviate the New User Cold-Starting Problem," Information Sciences, Vol. 128, 2008, pp. 37-51.
  3. Bell, R., Koren, Y., and Volinsky, C., "Chasing $1,000,000：How We Won the Netflix Progress Prize," Vol. 18, No. 2, December, 2007, pp. 4-12.
  4. Herlocker, J. L., et al., "An Algorithmic Framework for Performing Collaborative Filtering," Proceedings of the 22nd Annual International ACM SIGIR Conf. on Research and Development in Information Retrieval, Berkeley, USA, 1999, pp. 230-237.
  5. Herlocker, J. L., et al., "Evaluating Collaborative Filtering Recommender Systems," ACM Transactions on Information Systems, Vol. 22, No. 1, 2004, pp. 5-53. https://doi.org/10.1145/963770.963772
  6. Jaschke, R., et al., "Tag Recommendations in Folksonomies," Proceedings of the PKDD 2007 (LNAI 4702), 2007, pp. 506-514.
  7. Ji, A.-T., et al., "Collaborative Tagging in Recommender Systems," Proceedings of AI 2007 (LNAI 4830), 2007, pp. 377-386.
  8. Kim, H. -N., et al., "Error-Based Collaboration Filtering Algorithm for Top-N Recommendation," Proceedings of APWeb 2007 and WAIM 2007 (LNCS 4505), pp. 594-605, Huang Shan, China, June, 2007, pp. 16-18.
  9. Konstan, J., et al., "GroupLens：Applying Collaborative Filtering to Usenet News," Communications of the ACM, Vol. 40, No. 3, 1997, pp. 77-87. https://doi.org/10.1145/245108.245126
  10. Lee, H. C., Lee, S. J., and Chung Y. J., "A Study on the Improved Collaborative Filtering Algorithm for Recommender System," Proceedings of the 5th International Conference on Software Engineering Research, Management and Applications (SERA2007), 2007, pp. 297-304.
  11. Mika, P., "Ontologies Are Us：A Unified Model of Social Networks and Semantics," Proceedings of the ISWC 2005 (LNCS 3729), 2005, pp. 522-536.
  12. Nakamoto, R., et al., "Tag-Based Contextual Collaborative Filtering," Proceedings of DEWS2007, Hiroshima, Japan, 2007, pp. 25-30.
  13. Netflix, "Netflix Prize," http://www.netflixprize.com//index, 2006.
  14. Paterek, A., "Improving Regularized Singular Value Decomposition for Collaborative Filtering," Proceedings of the KDD Cup and Workshop, San Jose, California, USA, August 12, 2007.
  15. Rhie, B. W., Kim, J. W., and Lee H. J., "Methods of User-Created Content Recommendation with Content Metadata," Proceedings of the Asian e-Biz Workshop, 2008.
  16. Sarwar B., et al., "Analysis of Recommendation Algorithms for e-Commerce," Proceedings of the 2nd ACM Conf. on Electronic Commerce, Minneapolis, USA, 2000, pp. 158-167.
  17. Sarwar, B., Karypis, G., Konstan, J., and Reidl, J., "Item-Based Collaborative Filtering Recommendation Algorithms," Proceedings of the 10th Int'l WWW Conf., Hong Kong, May 1-5, 2001, pp. 285-295.
  18. Shardanand, U., and Maes, P., "Social Information Filtering：Algorithms for Automating 'Word of Mouth'," Proceedings of the ACM CHI Conf. on Human Factors in Computing Systems, Denver, USA, May 1995, pp. 210-217.
  19. Tso-Sutter, K. H. L., Marinho, L. B., and Schmidt-Thieme, L., "Tag-aware Recommender Systems by Fusion of Collaborative Filtering Algorithms," Proceedings of the SAC'08, Brazil, March 2008.