Abstract
Geographical characteristics have been proven to be effective in improving the quality of point-of-interest (POI) recommendation. However, existing works on POI recommendation focus on cost (time or money) of travel for a user. An important geographical aspect that has not been studied adequately is the neighborhood effect, which captures a user's POI visiting behavior based on the user's preference not only to a POI, but also to the POI's neighborhood. To provide an interpretable framework to fully study the neighborhood effect, first, we develop different sets of insightful features, representing different aspects of neighborhood effect. We employ a Yelp data set to evaluate how different aspects of the neighborhood effect affect a user's POI visiting behavior. Second, we propose a deep learning-based recommendation framework that exploits the neighborhood effect. Experimental results show that our approach is more effective than two state-of-the-art matrix factorization-based POI recommendation techniques.
Highlights
Location-based social networks (LBSNs) facilitate personalized point-of-interest (POI) recommendation, which helps users in exploring interesting places, and increases revenues for businesses
Our model outperforms two state-of-the-art matrix factorization–based approaches, demonstrating the effectiveness of integrating neighborhood features in a deep neural network for POI recommendation
We propose a deep neural network–based POI recommender that incorporates the neighborhood effect and improves precision and recall of POI recommendation compared to the state-of-the-art matrix factorization models
Summary
Location-based social networks (LBSNs) facilitate personalized point-of-interest (POI) recommendation, which helps users in exploring interesting places, and increases revenues for businesses. Approaches that rely only on the check-in matrix yield poor recommendation quality [1]. Additional context information such as social relationships [2] and geographical characteristics [3] have been exploited to overcome the data sparsity problem and improve the recommendation quality. The neighborhood effect is different from the geographical effect investigated in previous studies. Those studies assume that users tend to visit POIs near their homes or offices and nearby POIs of a POI that they just visited [4, 5].
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call