摘要
当前最新的兴趣点推荐工作开始融合地理、文本和社交信息进行推荐,但是还存在信息挖掘不充分的情况。为此,提出了改进的多类型信息融合的联合概率生成的兴趣点推荐模型。首先提出了自动学习文档话题数目的分层狄利克雷过程主题模型,学习用户和兴趣点相关兴趣话题;同时,利用由签到分布决定带宽大小的核密度估计法,个性化地理信息对用户签到行为的影响,而且还融合了用户位置访问序列中已访问兴趣点对待访问兴趣点的影响,即序列模式的影响;然后综合考虑了用户社交关系的影响;最后基于联合概率生成模型,融合文本、地理、社会和序列信息,提出TGSS-PGM兴趣点推荐模型,依据计算结果从而生成兴趣点推荐列表推荐给用户。实验结果表明,该模型在推荐准确率等多种评价指标上都取得了更好的结果。
The state-of-the-art studies started paying attention to comprehensively analyze geographical information,comment information and social information,but there is still insufficient information mining. To this end,this paper proposed a joint probabilistic generative model of multi-information fusion. Firstly,the framework learned interest topics of users and POIs through textual information,by exploiting the aggregated hierarchical Dirichlet process model,which could automatically learn the number of topics,to replace latent Dirichlet allocation model. Secondly,according to the kernel density estimation method,whose bandwidth depended on the check-in distribution,the framework conducted personalized modeling of geographic information. Thirdly,it also took consideration of sequential patterns,which was the impact of the visited location to the non-visited location. Then,it modeled social relevance comprehensively. At last,based on the joint probabilistic generative model,this paper proposed the TGSS-PGM model,exploiting multi-type contextual information and incorporating these factors effectively. Experimental results in real world social network show that the proposed model outperforms state-of-the-art recommendation algorithms in terms of precision and rating error.
引文
[1]任星怡,宋美娜,宋俊德.基于用户签到行为的兴趣点推荐[J].计算机学报,2017,40(1):28-51.
[2]刘少鹏,印鉴,欧阳佳,等.基于MB-HDP模型的微博主题挖掘[J].计算机学报,2015,38(7):1408-1419.
[3]Liu Bin,Fu Yanjie,Yao Zijun,et al.Learning geographical preferences for point-of-interest recommendation[C]//Proc of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2013:1043-1051.
[4]Yang Dingqi,Zhang Daqing,Yu Zhiyong,et al.A sentiment-enhanced personalized location recommendation system[C]//Proc of the 24th ACM Conference on Hypertext and Social Media.New York:ACM Press,2013:119-128.
[5]李鑫.基于位置社交网络的地点推荐方法及应用研究[D].合肥:中国科学技术大学,2015.
[6]Yin Hongzhi,Sun Yizhou,Cui Bin,et al.LCARS:a location-contentaware recommender system[C]//Proc of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2013:221-229.
[7]任星怡,宋美娜,宋俊德.基于位置社交网络的上下文感知的兴趣点推荐[J].计算机学报,2017,40(4):824-841.
[8]Ye Mao,Yin Peifeng,Lee W C,et al.Exploiting geographical influence for collaborative point-of-interest recommendation[C]//Proc of the 34th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York:ACM Press,2011:325-334.
[9]Cheng Chen,Yang Haiqin,King I,et al.Fused matrix factorization with geographical and social influence in location-based social networks[C]//Proc of the 26th AAAI Conference on Artificial Intelligence.Palo Alto,CA:AAAI Press,2012:17-23.
[10]Zhang Jiadong,Chow C,Li Yanhua.i GeoRec:a personalized and efficient geographical location recommendation framework[J].IEEE Trans on Services Computing,2015,8(5):701-714.
[11]Zheng Yantao,Zha Zhengjun,Chua T S.Mining travel patterns from geotagged photos[J].ACM Trans on Intelligent Systems&Technology,2012,3(3):338-343.
[12]Cheng Anjung,Chen Yanying,Huang Yenta,et al.Personalized travel re-commendation by mining people attributes from community-contributed photos[C]//Proc of the 19th ACM International Conference on Multimedia.New York:ACM Press,2011:83-92.
[13]Cheng Chen,Yang Haiqin,Lyu M R,et al.Where you like to go next:successive point-of-interest recommendation[C]//Proc of the 23rd International Joint Conference on Artificial Intelligence.Palo Alto,CA:AAAI Press,2013.
[14]Zhang Jiadong,Chow C Y,Li Yanhua.LORE:exploiting sequential influence for location recommendations[C]//Proc of the 2nd ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:ACM Press,2014:103-112.
[15]Chen Zaiben,Shen Hengtao,Zhou Xiaofang.Discovering popular routes from trajectories[C]//Proc of IEEE International Conference on Data Engineering.Piscataway,NJ:IEEE Press,2011:900-911.
[16]Kurashima T,Iwata T,Irie G,et al.Travel route recommendation using geotags in photo sharing sites[C]//Proc of the 19th ACM International Conference on Information and Knowledge Management.New York:ACM Press,2010:579-588.
[17]Bao Jie,Zheng Yu,Mokbel M F,et al.Location-based and preferenceaware recommendation using sparse geo-social networking data[C]//Proc of the 20th International Conference on Advances in Geographic Information Systems.New York:ACM Press,2012:199-208.
[18]Gao Huiji,Tang Jiliang,Liu Huan.g SCorr:modeling geo-social correlations for new check-ins on location-based social networks[C]//Proc of the 21st ACM International Conference on Information and Knowledge Management.New York:ACM Press,2012:1582-1586.
[19]Kurashirna T,Iwata T,Hoshide T,et al.Geo topic model:joint modeling of user’s activity area and interests for local recommendation[C]//Proc of the 6th ACM International Conference on Web Search and Data Mining.New York:ACM Press,2013:375-384.
[20]Wang Hao,Terrovitis M,Mamoulis N.Location recommendation in location-based social networks using user check-in data[C]//Proc of the21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:ACM Press,2013:374-383.
[21]Zhang Jiadong,Chow C Y.i GSLR:personalized geo-social location recommendation:a kernel density estimation approach[C]//Proc of the21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:ACM Press,2013:334-343.
[22]Yin Hongzhi,Cui Bin,Sun Yizhou,et al.Pollari K.LCARS:a spatial item recommender system[J].ACM Trans on Information Systems,2014,32(3):Article No.11.