个性化地点推荐系统对于基于位置的社交网络(Location-based Social Networks, LBSNs)的发展至关重要.它不仅能够帮助用户挖掘新的地点,同时也有利于服务商更好地提供个性化服务.现存关于这方面的研究,将所有的地点同等看待.但是在不同类别中,签到频率的数据规模却不可同等看待.本文基于TF-IDF理论将签到频率转换成基于类别的偏好数据,提出一个基于地理邻近性的深度自编码器模型,利用签到数据中的地理信息构造推荐系统.在LBSNs真实数据集上进行实验分析,结果表明相对于对比算法,本文模型的实验结果更好,基于地理邻近性的深度自编码器模型适用于地点推荐任务.%Personalized point-of-interest(POI)recommendation is crucial to the development of location-based social networks (LBSNs).It not only helps users explore new places but also enables third -party services to better provide service.Previous stud-ies on this topic treat all POIs as equal.Learning preferences within category makes sense,but the scale in which the frequency of check-ins operates is not comparable across categories.In this paper,we transform the check-in frequency into category-based preference according to TF-IDF theory.And then we propose a Geo-DAE model for the geographical proximity among POIs.The experimental results based on datasets from real-world LBSNs show that the proposed model achieves better performance than other state-of-the-art methods,and the proposed model is a better alternative for POI recommendation.
展开▼
