Abstract:
With the rapid development of Location-based social networks (LBSN), there is a growing demand for location services. How to use the users' historical check-in data for e...Show MoreMetadata
Abstract:
With the rapid development of Location-based social networks (LBSN), there is a growing demand for location services. How to use the users' historical check-in data for exploring their visit patterns and preference characteristics to realize personalized point-of-interest (POI) recommendation has become an important topic. Finding valid features from the check-in data is the key to POI recommendation. Deep learning is a multi-level representation learning method, which can better explore the relationship between features. Therefore, a new POI recommendation model named DLM based on deep neural network is proposed in this paper. This model incorporates topic features, user preference features and geographical factor features in the LBSN into the POI recommendation tasks, thereby it improves the efficiency of users' personalized POI recommendation. A lot of experiments on public data set Foursquare have proved the advantages and effectiveness of the proposed method.
Published in: 2019 6th International Conference on Behavioral, Economic and Socio-Cultural Computing (BESC)
Date of Conference: 28-30 October 2019
Date Added to IEEE Xplore: 20 January 2020
ISBN Information: