Unified Point-of-Interest Recommendation with Temporal Interval Assessment
published: Sept. 27, 2016, recorded: August 2016, views: 41
Report a problem or upload filesIf you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Point-of-interest (POI) recommendation, which helps mobile users explore new places, has become an important location-based service. Existing approaches for POI recommendation have been mainly focused on exploiting the information about user preferences, social inﬂuence, and geographical inﬂuence. However, these approaches cannot handle the scenario where users are expecting to have POI recommendation for a speciﬁc time period. To this end, in this paper, we propose a uniﬁed recommender system, named the ‘Where and When to gO’ (WWO) recommender system, to integrate the user interests and their evolving sequential preferences with temporal interval assessment. As a result, the WWO system can make recommendations dynamically for a speciﬁc time period and the traditional POI recommender system can be treated as the special case of the WWO system by setting this time period long enough. Speciﬁcally, to quantify users’ sequential preferences, we consider the distributions of the temporal intervals between dependent POIs in the historical check-in sequences. Then, to estimate the distributions with only sparse observations, we develop the low-rank graph construction model, which identiﬁes a set of bi-weighted graph bases so as to learn the static user preferences and the dynamic sequential preferences in a coherent way. Finally, we evaluate the proposed approach using real-world data sets from several location-based social networks (LBSNs). The experimental results show that our method outperforms the state-of-the-art approaches for POI recom-mendation in terms of various metrics, such as F-measure and NDCG, with a signiﬁcant margin.
Link this pageWould you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !