Point-of-Interest Recommendations via a Supervised Random Walk Algorithm

Recently, location-based social networks (LBSNs) such as Foursquare and Whrrl have emerged as a new application for users to establish personal social networks and review various points of interest (POIs), triggering a new recommendation service aimed at helping users locate more preferred POIs. Although users' check-in activities could be explicitly considered as user ratings, in turn being utilized directly for collaborative filtering-based recommendations, such solutions don't differentiate the sentiment of reviews accompanying check-ins, resulting in unsatisfactory recommendations. This article proposes a new POI recommendation framework by simultaneously incorporating user check-ins and reviews along with side information into a tripartite graph and predicting personalized POI recommendations via a sentiment-supervised random walk algorithm. The experiments conducted on real data demonstrate the superiority of this approach in comparison with state-of-the-art techniques.

Authors

• Guandong Xu University of Technology Sydney The Education University of Hong Kong
• Bin Fu Institute of Computing Technology, Chinese Academy of Sciences University of Chinese Academy of Sciences
• Yanhui Gu School of Computer and Electronic Information Science, Nanjing Normal University

Keywords

• Social network services
• Mathematical model
• Mobile communication
• Analytical models
• Behavioral science
• Recommender systems
• Random Walk
• Random Walk Algorithm
• Social Networks
• Sparsity
• Social Influence
• Transition Probabilities
• Point Of Interest
• Mobile Users
• Wireless Technologies
• Random Walk Model
• Positive Reviews
• User Reviews
• Sentiment Polarity
• Cold-start Problem
• Cut-off Value
• Negation
• Specific Topics
• Mutual Information
• Social Information
• Vector Of Length
• Pointwise Mutual Information
• User Preferences
• Positive Polarity
• Negative Words
• Positive Words
• Sentiment Analysis
• Negative Comments
• Precision Ratio
• Positive Comments
• points of interest
• POIs
• sentiment
• recommender system
• supervised random walk
• intelligent systems