Journal of KIISE:Computing Practices and Letters (한국정보과학회논문지:컴퓨팅의 실제 및 레터)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Improvement on Similarity Calculation in Collaborative Filtering Recommendation using Demographic Information

인구 통계 정보를 이용한 협업 여과 추천의 유사도 개선 기법

  • 이용준 (한국전기연구원 전기시험연구소) ;
  • 이세훈 (인하공업전문대학 컴퓨터정보공학부) ;
  • 왕창종 (인하대학교 컴퓨터공학부)
  • Published : 2003.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper we present an improved method by using demographic information for overcoming the similarity miss-calculation from the sparsity problem in collaborative filtering recommendation systems. The similarity between a pair of users is only determined by the ratings given to co-rated items, so items that have not been rated by both users are ignored. To solve this problem, we add virtual neighbor's rating using demographic information of neighbors for improving prediction accuracy. It is one kind of extentions of traditional collaborative filtering methods using the peason correlation coefficient. We used the Grouplens movie rating data in experiment and we have compared the proposed method with the collaborative filtering methods by the mean absolute error and receive operating characteristic values. The results show that the proposed method is more efficient than the collaborative filtering methods using the pearson correlation coefficient about 9% in MAE and 13% in sensitivity of ROC.

본 논문에서는 추천시스템에서 많이 활용되는 협업 여과 방법의 문제점으로 지적되고 있는 희소성(sparsity)으로 인한 유사도의 부정확한 문제를 개선하기 위하여, 인구 통계 정보를 이용한 기법을 제안하였다. 두 사용자간의 유사도는 같은 항목에 동시에 평가된 점수를 기반으로 결정되며, 두 사용자가 동시에 평가하지 않은 항목은 유사도 계산에서 제외된다. 제안된 기법은 이러한 평가 점수 부족으로 인하여 유사도 계산이 정확치 못한 단점을 보완하기 위하여, 인구 통계 정보를 이용한 가상 평가 점수를 부가하여 유사도 계산을 개선, 예측의 정확도를 향상시킨 방식으로 기존의 피어슨 상관관계를 이용한 협업여과 방식의 확장이다. 실험은 Grouplens의 영화 평가 자료를 활용하였고, 평균절대오차(MAE)와 반응자 작용특성(ROC)값을 이용하여 제안 기법과 피어슨 상관관계를 이용한 협업 여과 방식을 비교하였다. 제안한 기법이 피어슨 상관관계를 이용한 협업 여과 추천 방식에 비하여 평균절대오차는 9%, 반응자 작용 특성의 민감도는 13% 향상되었음을 확인하였다.

Keywords

References

  1. Miller,B., Riedl,J. and Konstan,J., 'Experiences with GroupLens:Making Usenet useful again,' Proc. of the 1997 Usenix Winter Technical Conference, pp.219-231, 1997
  2. Ansari,A., Essegaier,S. and RKohli,R., 'Internet Recommendation Systems,' Journal of Marketing Reserch Vol.37, pp. 363-375, 2000 https://doi.org/10.1509/jmkr.37.3.363.18779
  3. Il Im, 'Augmenting Knowledge Reuse Using Collaborative Filtering Systems,' A Dissertation Presented to the faculty of the graduate school USC (Information Systems), p.191, 2001
  4. Basu,C., Hirsh,H. and Cohen,W, 'Recommendation as Classification: Using Social and Content-based Information in Recommendation,' Proc, of the Fifteenth National Conference on Artificial Intelligence(AAAI-98), pp.714-720, 1998
  5. Pazzani,M., 'A Framework for Collaborative, Content-Based and Demographic Filtering,' Artificial Intelligent Review 13(5-6), pp.393-408, 1999 https://doi.org/10.1023/A:1006544522159
  6. Goldberg,D., Nichols,D., Oki,B.M. and Terry.D., 'Using Collaborative Filtering to Weave an Information Tapestry,' Communications of the ACM, Vol.35 No.12, pp. 61-70, 1992 https://doi.org/10.1145/138859.138867
  7. Konstan,J., Miller,B., Maltz,D., Herlocker,J., Gordon,K. and Riedl,J. 'GroupLens .Applying Colla borative Filtering to Usenet News,' Communications of the ACM, Vol.40 No.3, pp.77-87, 1997 https://doi.org/10.1145/245108.245126
  8. Rensnick,P., Iacovou,N., Suchak,M., Nergstorm,P. and Riedl,J. 'GroupLens : An Open Architecture for Collaborative Filtering of Netnews,' Proc. of CSCW '94, pp. 175-186, 1994 https://doi.org/10.1145/192844.192905
  9. Shardanand,U. and Maes,P., 'Social information filtering : Algorithms for automating 'word of mouth',' Proc. of ACM CHI '95 Conference on Human Factors in Computing Systems, pp.210-217, 1995 https://doi.org/10.1145/223904.223931
  10. Breese,J., Heckerman,D. and Kadie,C., 'Empirical Analysis of Prediction Algorithms for Collaborative Filtering,' Proc. of the 14th Conference on Uncertainly in Artificial Intelligence, pp.43-52, 1998
  11. O'conner,M. and Herlocker.J, 'Clustering Items for Collaborative Filtering,' ACM SIGIR '99, http://www.csee.umbc.edu/~ian/sigir99-rec/, 1999
  12. Proc. of CHI ‘95 Conference on Human Factors in Computing Systems Recommending and Evaluating Choices in a Virtual Community of Use Hill,W.;Stead,L.;Rosenstein,M.;Furnas,G.
  13. Hill,W., Stead,L., Rosenstein,M. and Furnas,G., 'Recommending and Evaluating Choices in a Virtual Community of Use,' Proc. of CHI '95 Conference on Human Factors in Computing Systems, pp.194-201, 1995 https://doi.org/10.1145/223904.223929
  14. Goldberg,K., Roeder,T, Gupta.D, and Perkins,C. 'Eigentaste: A Constant Time Collaborative Filtering Algorithms,' Information Retrieval Vol.4, No.2, pp.133-151, 2001 https://doi.org/10.1023/A:1011419012209
  15. Melville,P., Mooney,R. and Nagarajan,R., 'Content-Boosted Collaborative Filtering for Improved Recommendations,' Proc. of the 8th National Conference on Artificial Intelligence(AAAI-2002), pp.187-192, 2002
  16. Andrew,I., Popescul,A. and Ungar,L., 'Methods and Metrics for Cold-Start Recommendations,' Proc. of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp.253-260, 2002 https://doi.org/10.1145/564376.564421
  17. Herlocker,j., Konstan,J., Borchers,A. and Riedl,J., 'An Algorithmic Framework for Performing Collaboraive Filtering,' Proc. of the 1999 Conference on Research and Development in Information Retrieval. ACM Press, NY, pp.203-237, 1999 https://doi.org/10.1145/312624.312682
  18. Sarwar,B., Karypis,G., Konstan,J. and Riedl,J., 'Item based collaborative filtering recommendation algorithms,' Proc. of the 10th International World Wide Conference, pp.285-295, 2001 https://doi.org/10.1145/371920.372071
  19. Sarwar,B., Karypis,G., Konstan,J. and Riedl,J. 'Application of Dimensionality Reduction in Recommendation System- A Case Study,' ACM WebKDD 2000 Web Mining for E-Commerce Workshop, http://robotics.stanford.edu/~ronnyk/WEBKDD2000/papers/, 2000
  20. Good,N., Schafer,B., Konstan,J., Borchers,A. Sarwar,B., Herlocker,J. and Riedle,J., 'Combining Collaborative Filtering with Personal Agents for Better Recommendation,' Proc. of the AAAI conference. pp. 439-446, 1999
  21. Claypool,M., Brown,D., Phong.L. and Waseda,M. 'Infering User Interest,' Computer Science Technical Report Series WPI-CS-TR-01-07, p.23, Worcester Polytechnic Institute, 2001
  22. Sarwar,B., Karypis,G., Konstan,J. and Riedl,J., 'Getting to Know you :Learning New User Preferences in Recommender System for Groups of Users,' Proc. of the 7th International conference on Intelligent user interfaces, pp.127-134, 2002 https://doi.org/10.1145/502716.502737
  23. http://www.grouplens.org