LBSN中融合时空信息的连续兴趣点推荐

针对位置社交网络（location-based social networks，LBSN）中连续兴趣点（point-of-interest，POI）推荐系统面临的数据稀疏性、签到数据的隐式反馈属性、用户的个性化偏好等挑战，提出一种融合时空信息的连续兴趣点推荐算法。该算法将用户的签到行为建模为用户—当前兴趣点—下一个兴趣点—时间段的四阶张量，并利用LBSN中的地理信息定义用户访问兴趣点的地理距离偏好，最后采用BPR（Bayesian personalized ranking）标准优化目标函数。实验结果表明该算法相比其他先进的连续兴趣点推荐算法具有更好的推荐效果。

Successive point-of-interest recommendation with spatial-temporal influence in LBSN

This paper studied the successive POI recommendation problem in location-based social networks and the challenge lies in the data sparsity, implicit user feedback and personalized preference. To this end, the paper proposed a novel model for successive POI recommendation, which integrated temporal information and geographical influence. Specifically, the paper modeled the successive check-in behaviors as a fourth-order tensor and employed geographical influence to define the spatial preference of the user for the POI. Then it utilized Bayesian personalized ranking criterion to optimize the loss objective function. Experimental results demonstrate that the proposed model outperforms the state-of-the-art successive POI recommendation methods.