基于用户兴趣相似度与熟悉度的兴趣点推荐算法
|
摘要
在兴趣点推荐中,由于用户签到矩阵的稀疏性问题,基于协同过滤的兴趣点推荐算法难以准确计算用户相似度,导致推荐效果不理想。论文提出一种基于用户兴趣相似度和熟悉度的兴趣点推荐算法,能在稀疏的数据集上计算用户相似性,改善邻近用户搜索质量,提高推荐准确率。实验结果表明,论文方法与其他矩阵分解算法相比具有更好的推荐效果。
In the POI(Point of Interest)recommendation,there is a problem in precisely calculating users'similarity owning to the sparseness of check-in data,which results in the poor recommendation.An algorithm based on users'interest similarity and familiarity is proposed in this paper,this new approach works more effectively in calculating users'similarity,improves quality of similar users and accuracy of recommendation results.The experiment shows that this new approach achieves superior recommendation quality compared to others matrix factorization algorithms.
In the POI(Point of Interest)recommendation,there is a problem in precisely calculating users'similarity owning to the sparseness of check-in data,which results in the poor recommendation.An algorithm based on users'interest similarity and familiarity is proposed in this paper,this new approach works more effectively in calculating users'similarity,improves quality of similar users and accuracy of recommendation results.The experiment shows that this new approach achieves superior recommendation quality compared to others matrix factorization algorithms.
引文
[1]Ding Y,Li X. Time weight collaborative filtering[C]//Proc. of the ACM International Conference on Information&Knowledge Management,2005(1):485-492.
[2]Koren Y. Collaborative filtering with temporal dynamics[J]. Communications of the Acm,2009,53(4):89-97.
[3]Jamali M,Ester M. TrustWalker:a random walk modelfor combining trust-based and item-based recommenda-tion[C]//ACM SIGKDD International Conference onKnowledge Discovery and Data Mining. ACM,2009:397-406.
[4] Jiang S,Qian X,Shen J,et al. Author Topical Mod-el-Based Collabarative Filtering for Personalized POI Rec-ommendations[J]. IEEE Transactions on Multimedia,2015,17(6):907-918
[5]张忠平,郭献丽.一种优化的基于项目评分预测的协同过滤推荐算法[J].计算机应用研究,2008,25(9):2658-2660.ZHANG Zhongping,GUO Xianli. An Optimized Collabor-ative Filtering Recommendation Algorithm Based on Proj-ect Scoring Prediction[J].Application Research of Com-puters,2008,25(9):2658-2660.
[6]Ke X. A Social Networking Services System Based on the"Six Degrees of Separation Theory and Damping Factors[C]//International Conference on Future Networks.IEEE,2010:438-441.
[7]Walker S K. Connected:The Surprising Power of Our So-cial Networks and How They Shape Our Lives[J]. Journal of Family Theory&Review,2011,3(3):220-224.
[8]Ye M,Yin P,Lee W C. Location recommendation for lo-cation-based social networks[C]//ACM Sigspatial Inter-national Symposium on Advances in Geographic Informa-tion Systems,Acm-Gis 2010,November 3-5,2010,SanJose,Ca,Usa,Proceedings. DBLP,2010:458-461.
[9]Ye,Mao,Yin,et al. Exploiting geographical influencefor collaborative point-of-interest recommendation[J].2011:325-334.
[10]Cho E,Myers S A,Leskovec J. Friendship and mobility:user movement in location-based social networks[C]//ACM SIGKDD International Conference on KnowledgeDiscovery and Data Mining,San Diego,Ca,Usa,Au-gust. DBLP,2011:1082-1090.
[11]Cheng C,Yang H,King I,et al. Fused matrix factoriza-tion with geographical and social influence in loca-tion-based social networks[C]//AAAI Conference on Ar-tificial Intelligence,2012.
[12]Zhang J,Chowmember C,Li Y. iGeoRec:A Personalized and Efficient Geographical Location Recommenda-tion Framework[J]. Services Computing IEEE Transac-tions on,2014,8(5):701-714.
[13]Y. Shi,P. Serdyukov,A. Hanjalic,et al. Personalizedlandmark recommendation based on geotags from photosharing sites[C]//International Conference on Weblogsand Social Media,Barcelona,Catalonia,Spain,July.DBLP,2011.
[14]孙光福,吴乐,刘淇,等.基于时序行为的协同过滤推荐算法[J].软件学报,2013(11):2721-2733.SUN Guangfu,WU Le,LIU Qi,et al. Collaborative Fil-tering Recommendation Algorithm Based on Time SeriesBehavior[J].Journal of Software,2013(11):2721-2733.
[15]Berjani B,Strufe T. A recommendation system for spotsin location-based online social networks[C]//The Work-shop on Social Network Systems. ACM,2011:1-6.
[16]Leung W T,Lee D L,Lee W C. CLR:a collaborative lo-cation recommendation framework based on co-clustering[C]//ACM,2011:305-314.
[2]Koren Y. Collaborative filtering with temporal dynamics[J]. Communications of the Acm,2009,53(4):89-97.
[3]Jamali M,Ester M. TrustWalker:a random walk modelfor combining trust-based and item-based recommenda-tion[C]//ACM SIGKDD International Conference onKnowledge Discovery and Data Mining. ACM,2009:397-406.
[4] Jiang S,Qian X,Shen J,et al. Author Topical Mod-el-Based Collabarative Filtering for Personalized POI Rec-ommendations[J]. IEEE Transactions on Multimedia,2015,17(6):907-918
[5]张忠平,郭献丽.一种优化的基于项目评分预测的协同过滤推荐算法[J].计算机应用研究,2008,25(9):2658-2660.ZHANG Zhongping,GUO Xianli. An Optimized Collabor-ative Filtering Recommendation Algorithm Based on Proj-ect Scoring Prediction[J].Application Research of Com-puters,2008,25(9):2658-2660.
[6]Ke X. A Social Networking Services System Based on the"Six Degrees of Separation Theory and Damping Factors[C]//International Conference on Future Networks.IEEE,2010:438-441.
[7]Walker S K. Connected:The Surprising Power of Our So-cial Networks and How They Shape Our Lives[J]. Journal of Family Theory&Review,2011,3(3):220-224.
[8]Ye M,Yin P,Lee W C. Location recommendation for lo-cation-based social networks[C]//ACM Sigspatial Inter-national Symposium on Advances in Geographic Informa-tion Systems,Acm-Gis 2010,November 3-5,2010,SanJose,Ca,Usa,Proceedings. DBLP,2010:458-461.
[9]Ye,Mao,Yin,et al. Exploiting geographical influencefor collaborative point-of-interest recommendation[J].2011:325-334.
[10]Cho E,Myers S A,Leskovec J. Friendship and mobility:user movement in location-based social networks[C]//ACM SIGKDD International Conference on KnowledgeDiscovery and Data Mining,San Diego,Ca,Usa,Au-gust. DBLP,2011:1082-1090.
[11]Cheng C,Yang H,King I,et al. Fused matrix factoriza-tion with geographical and social influence in loca-tion-based social networks[C]//AAAI Conference on Ar-tificial Intelligence,2012.
[12]Zhang J,Chowmember C,Li Y. iGeoRec:A Personalized and Efficient Geographical Location Recommenda-tion Framework[J]. Services Computing IEEE Transac-tions on,2014,8(5):701-714.
[13]Y. Shi,P. Serdyukov,A. Hanjalic,et al. Personalizedlandmark recommendation based on geotags from photosharing sites[C]//International Conference on Weblogsand Social Media,Barcelona,Catalonia,Spain,July.DBLP,2011.
[14]孙光福,吴乐,刘淇,等.基于时序行为的协同过滤推荐算法[J].软件学报,2013(11):2721-2733.SUN Guangfu,WU Le,LIU Qi,et al. Collaborative Fil-tering Recommendation Algorithm Based on Time SeriesBehavior[J].Journal of Software,2013(11):2721-2733.
[15]Berjani B,Strufe T. A recommendation system for spotsin location-based online social networks[C]//The Work-shop on Social Network Systems. ACM,2011:1-6.
[16]Leung W T,Lee D L,Lee W C. CLR:a collaborative lo-cation recommendation framework based on co-clustering[C]//ACM,2011:305-314.