A time-aware spatio-textual recommender system. (15th July 2017)

• Record Type: Journal Article
• Authors: Kefalas, Pavlos; Manolopoulos, Yannis
• Is Part Of: Expert systems with applications. Volume 78(2017)
• Page Start: 396
• Page End: 406
• Publication Date: 2017-07-15
• Subjects: Recommender systems -- Location based services -- Collaborative filtering -- Review recommendation -- Point-of-interest recommendation -- Spatio-textual analysis -- Temporal analysis; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2017.01.060
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: We present two novel unified models to provide review and POI recommendations. We consider simultaneously the spatial, the textual, and the temporal factor. We measure the temporal influence in each time interval for different range distances. Results indicate that the combination of the three dimensions exhibit higher accuracy. Abstract: Location-Based Social Networks (LBSNs) allow users to post ratings and reviews and to notify friends of these posts. Several models have been proposed for Point-of-Interest (POI) recommendation that use explicit (i.e. ratings, comments) or implicit (i.e. statistical scores, views, and user influence) information. However the models so far fail to capture sufficiently user preferences as they change spatially and temporally. We argue that time is a crucial factor because user check-in behavior might be periodic and time dependent, e.g. check-in near work in the mornings and check-in close to home in the evenings. In this paper, we present two novel unified models that provide review and POI recommendations and consider simultaneously the spatial, textual and temporal factors. In particular, the first model provides review recommendations by incorporating into the same unified framework the spatial influence of the users' reviews and the textual influence of the reviews. The second model provides POI recommendations by combining the spatial influence of the users' check-in history and the social influence of the users' reviews into another unified framework. Furthermore, for both models we consider the temporal dimension and measure the impact of time on various time intervals. We evaluate the performance of our models against 10 other methods in terms of precision and recall . The results indicate that our models outperform the other methods.