LBSN中基于加权异构信息网络的兴趣点推荐

Weighted Heterogeneous Information Networks Based Personalized Point-of-interest Recommendation System in LBSN

基于位置社交网络(location-based social network,LBSN)的兴趣点(point-of-int crest,POI)推荐存在以下挑战:LBSN中具有大量异构数据,其含有的丰富信息未得到充分利用;"用户-兴趣点"矩阵非常稀疏,不利于提取其对应的特征。因此,引入了加权异构信息网络(weighted heterogeneous information network,WHIN),并采用加权元路径处理LBSN中地理位置、社交关系和时间周期对用户偏好的影响。在此基础上,提出了一种基于改进的奇异值分解(singular value decomposition,SVD++)和因子分解机(factorization machines,FM)的个性化兴趣点推荐算法。通过在Go walla和Foursquare数据集上的数据实验,验证了基于SVD++&FM的兴趣点推荐算法能够取得较优的推荐效果。研究结果对使用异构数据构建更加有效的兴趣点推荐系统具有重要指导意义,并为LBSN网站的服务推荐提供重要的管理建议。

Personalized point-of-interest(POI)recommendation is crucial for location-based social networks(LBSNs),which not only helps users explore places but also enables many location-based services,e.g.,the targeting of mobile advertisements to users.However,personalized POI recommendation is highly challenging.LBSNs involve heterogeneous types of data,and the user-POI matrix is very sparse.To address these challenges,we analyze users’check-in behaviors in detail and introduce the concept of a weightedheterogencous information network(WHIN).Then,we employ a meta path based approach to model geographical and social influences and a weighted meta path approach to model temporal influences.We propose an HIN-based POI recommendation system,which consists of two components:improved singular value decomposition(SVD++)and factorization machines(FMs).For the similarity matrices that arc generated by each meta path,we perform SVD++to generate latent features for both users and POIs.With various meta-pathbased features,we exploit FM with the group lasso to automatically select features.The results of experiments on two real-world LBSNs,namely,Go walla and Foursquare,demonstrate that our method outperforms baseline methods in terms of accuracy.