摘要
随着基于位置的服务应用的日益普及,基于位置的社交网络(LBSN)已经吸引了大量用户在他们的偏好兴趣点签到,并和朋友分享他们访问这些兴趣点的经验,兴趣点推荐方法有助于帮助用户探索周边生活环境,提高生活质量。最近有一些研究表明在兴趣点推荐中使用嵌入技术一个提高兴趣点推荐的准确率和效率。然而,这些研究并没有将分层结构应用到嵌入技术当中。本文我们提出了一种基于分层嵌入技术的兴趣点推荐模型来进行兴趣点推荐,进一步优化了兴趣点推荐的准确率和效率。在真实大型数据集(Foursquare)上的实验结果表明,该模型在推荐准确率和召回率等评价指标上都取得了更好的结果。
With the increasing popularity of location-based service applications,location-based social networks (LBSN) have attracted a large number of users to sign in at their preferred points of interest and share their experiences with friends to visit these points of interest. To help users explore the surrounding living environment,improve the quality of life. Some studies have recently shown the use of embedded technology in point of interest recommendation to improve the accuracy and efficiency of a point of interest. However,these studies do not apply hierarchical structures to embedded technology. In this paper,we propose a point-of-interest recommendation model based on hierarchical embedding technology to further promote the accuracy and efficiency of POI. The experimental results on the real large data set (Foursquare) show that the model has achieved better results in the evaluation index such as recommendation Precision and Recall rate.
引文
[1]刘袁柳.面向LBSN的兴趣点和用户推荐方法研究[D].苏州:苏州大学,2015.
[2]Zhao Y L,Nie L,Wang X,et al.Personalized recommendations of locally interesting venues to tourists via cross-region community matching[J].ACMTransactions on Intelligent Systems and Technology,2014,5(3):50
[3]Gao H,Barbier G,,Goolsby R.Harnessing the crowdsourcing power of social media for disaster relief[J].IEEE Intelligent Systems,2011,26(3):10-14.
[4]Xie M,Yin H,Wang H,et al.Learning graph based poi embedding for location-based recommendation.In ACMInternational on Conference on Information and Knowledge Management,2016:15-24.
[5]M Xie,H Yin,F Xu,et al.Graph based metric embedding for next poi recommendation.In WISE,2016.
[6]Tang J,Qu M,Wang M,et al.Line:Largescale information network embedding.1067-1077.
[7]Chen S,Moore J L,Turnbull D,et al.Playlist prediction via metric embedding.In ACM Knowledge Discovery and Data Mining,2012:714-722.
[8]Tang J,Qu M,Wang M,et al.Line:Largescale information network embedding.1067-1077.
[9]Lu K,Zhang G,Li R,et al.Exploiting and exploring hierarchical structure in music recommendation.In:Information Retrieval Technology.2012:211-225.
[10]Wang S,Tang J,Wang Y.et al.Exploring implicit hierarchical structures for recommender systems.2015.
[11]V Wang P,Guo J,Lan Y,et al.Learning hierarchical representation model for next basket recommendation.In:SIGIR,2015::403-412.
[12]Maleszka M,Mianowska B,Nguyen,N.T.:A method for collaborative recommendation using knowledge integration tools and hierarchical structure of user profiles.Knowledge Based Systems,2013,47:1-13.
[13]Gao H,Tang J,Hu X,et al.Exploring temporal effects for location recommendation on location-based social networks[A].
[14]Lian D,Zhao C,Xie X,et al.Geo MF:joint geographical modeling and matrix factorization for pointof-interest recommendation[A].
[15]Wang S,Tang J,Wang Y,et al.Exploring implicit hierarchical structures for recommender systems[A].Yang Q,Wooldridge M.Proceedings of the 24th International Conference on Artificial Intelligence[C].Menlo Park:AAAI Press,2015:1813-1819.