Location-aware recommendation problems

Abstract

Recommendation problems have been extensively studied in many areas, e.g. product recommendation in E-commerce sites and location recommendation in location-based social sites. With the development of location-based services (LBS), location-aware recommendation problems have been an important direction of recommendation systems. In this thesis, three challenging location-aware recommendation problems are proposed and studied, (i) personalized location recommendation, (ii) group recommendation of venues and (iii) topic suggestion for micro-reviews.

Firstly, the personalized location recommendation problem is studied. Location recommendation is an important feature of social network applications and location-based services. Most existing studies focus on developing one single method or model for all users. By analyzing data from two real location-based social networks (Foursquare and Gowalla), we reveal that the decisions of users on place visits depend on multiple factors, and different users may be affected differently by these factors. We design a location recommendation framework that combines results from various recommenders that consider various factors. Our framework estimates, for each individual user, the underlying influence of each factor to her. Based on the estimation, we aggregate suggestions from different recommenders to derive personalized recommendations. Experiments on Foursquare and Gowalla show that our proposed method outperforms the state-of-the-art methods on location recommendation.

Next, we study the problem of recommending venues to groups of users and propose a Hierarchical Bayesian Geographical Model (HBGG) for this purpose. First, a generative group geographical topic model (GG) based on group membership and group mobility regions is designed. Through the shared latent group features, the group geographical model is combined with social-based collaborative filtering framework, which integrates social structure into one-class collaborative filtering. Experimental results on two real datasets show that our method outperforms the state-of-the-art group recommenders, especially on cold-start user groups.

Finally, topic suggestion for micro-reviews is investigated. Location-based social sites, such as Foursquare or Yelp allow users to check in at venues and leave a short commentary in the form of a micro-review. Micro-reviews are rich in content as they offer a distilled and concise account of user experience. We consider the problem of predicting the topic of a micro-review by a user who visits a new venue. Such a prediction can help users make informed decisions, and also help venue owners personalize users' experiences. However, topic modeling for micro-reviews is particularly difficult, due to their short and fragmented nature. We address this issue using pooling strategies, which aggregate micro-reviews at the venue or user level, and we propose novel probabilistic models based on Latent Dirichlet Allocation (LDA) for extracting the topics related to a user-venue pair. Our best topic model (Authority-Sentiment LDA) integrates influences from both venue inherent properties and user preferences, considering at the same the sentiment orientation of the users. Experimental results on real datasets demonstrate the superiority of this model; they also show that venue-inherent properties have higher influence on the topics of micro-reviews.