基于半受限玻尔兹曼机的个性化地点推荐
首发时间:2017-09-25
摘要:在基于位置的位置的社交网络(location-based social networks , LBSNs)中,个性化地点推荐系统扮演者至关重要的角色。个性化地点推荐系统不仅能够帮助用户挖掘新的地点,同时也有利于第三方服务商更好地提供个性化服务,如投放针对性的广告等。现存关于这方面的研究,主要利用用户在每个地点上的签到次数数据进行推荐,但是该文章认为,签到次数并不能完整地代表用户的喜好。该文章提出一种基于半受限玻尔兹曼机的地点推荐算法,即利用半受限玻尔兹曼机对签到数据中的地理信息进行建模,从而更好的处理地点推荐任务。该文章在真实数据集上进行实验分析,且实验结果表明:相对于几种典型的算法,该文章的方法得到了更好的表现,表明改论文提出的算法在地点推荐领域的优势。在最后,该文章对本研究进行了总结和展望。
For information in English, please click here
Semi-RBM for Point-of-Interest Recommendation
Abstract:Personalized point-of-interest (POI) recommendation plays an important role in location-based social networks (LBSNs). It not only helps users explore new places but also enables third-party services to better provide service such as targeted advertisements. Previous research studies on this topic mainly focus on check-in frequency but we argue that check-in frequency alone cannot entirely represent users\' preferences. In this paper, firstly, we use the semi-restricted Boltzmann machine to model the geographical proximity. Our experimental results using datasets from real-world LBSNs show that our method achieves better performance than other state-of-the-art methods, and our method has a lot of potential in POI recommendation. Conclusions and future works are also given in the end.
Keywords: POI recommendation, semi-RBM, utility theory, geographical proximity
引用
No.****
同行评议
共计0人参与
勘误表
基于半受限玻尔兹曼机的个性化地点推荐
评论
全部评论0/1000