基于用户兴趣和地理因素的兴趣点推荐方法  

Point of Interest Recommendation Based on User’s Interest and Geographic Factors

作　　者：苏畅[1] 武鹏飞 谢显中[1] 李宁 SU Chang;WU Peng-fei;XIE Xian-zhong;LI Ning(College of Computer Science and Technology,Chongqing University of Posts and Telecommunications,Chongqing 400065,China)

机构地区：[1]重庆邮电大学计算机科学与技术学院,重庆400065

出　　处：《计算机科学》2019年第4期228-234,共7页Computer Science

基　　金：国家自然科学基金(61271259);重庆市基础科学与前沿技术研究项目(CSTC2016jcyA0398;CTSC2011jjA40006;CTSC2012jjA40038);重庆教育委员会研究项目(KJ120501C)资助

摘　　要：在基于位置的社交网络中,协同过滤作为目前应用最广泛的推荐技术,存在数据稀疏性和冷启动等问题。针对协同过滤算法的不足,提出了一种结合用户兴趣和地理因素的兴趣点推荐算法。该方法首先通过自适应带宽的核密度分布、朴素贝叶斯算法以及兴趣点的流行度挖掘用户的地理偏好,并根据地理偏好模型筛选出一部分候选推荐兴趣点;然后,为了克服协同过滤算法的数据稀疏性问题和用户冷启动问题,结合用户签到相似性、类别信息和用户信任度构建用户偏好模型进行兴趣点推荐;最后,使用Yelp数据集进行实验分析,结果表明所提出的基于用户兴趣和地理因素的兴趣点推荐模型取得了良好的推荐效果。In the location-based social network,collaborative filtering is the most widely used recommended technology,but it has some drawbacks,such as data sparsity and cold start.In light of this,this paper presented a point of interest(POI) recommendation algorithm combining user’s interest and geographic factors.In this method,firstly,the adaptive kernel density distribution,naive Bayesian algorithm and the popularity of POIs are combined to mine user’s geographi-cal preferences ,and some candidate recommended POIs are screened out according to the geographical preference model. Then ,in order to overcome the problems of data sparsity and cold start in collaborative filtering algorithm,a user pre-ference model is constructed to carry out POI recommendation based on the similarities of user checked-in,category information and user trust.Finally,the Yelp data set was used to conduct the experimental analysis.The results show that the proposed POI recommendation model based on user’s interest and geographical factor obtains good recommendation effect.

关 键 词：兴趣点推荐 地理偏好 类别信息 信任关系 协同过滤 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]