Recommendations based on user effective point-of-interest path
- PDF / 2,036,483 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 71 Downloads / 169 Views
ORIGINAL ARTICLE
Recommendations based on user effective point-of-interest path Guoqiang Zhou1 · Shuai Zhang1 · Yi Fan1 · Jingjin Li1 · Wenbo Yao1 · Hongfang Liu1 Received: 19 September 2017 / Accepted: 20 December 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract Point-of-interest (POI) recommendation has become an important service in location-based social networks. Existing recommendation algorithms provide users with a diverse pool of POIs. However, these algorithms tend to generate a list of unrelated POIs that user cannot continuously visit due to lack of appropriate associations. In this paper, we first proposed a concept that can recommend POIs by considering both category diversity features of POIs and possible associations of POIs. Then, we developed a top-k POI recommendation model based on effective path coverage. Moreover, considering this model has been proven to be a NP-hard problem, we developed a dynamic optimization algorithm to provide an approximate solution. Finally, we compared it with two popular algorithms by using two real-world datasets, and found that our proposed algorithm has better performance in terms of diversity and precision. Keywords Location-based social networks · Effective path coverage · Recommendation algorithm · Point-of-interest
1 Introduction With the rapid development of location-based social networks (LBSNs) (e.g., public scoring web, Foursquare, Gowalla and Facebook), users are able to share their experience and opinions by rating or evaluating certain content on the Internet through their social network accounts, such rating information typically includes time, location, users! personal information and evaluation data, and as a result, it will generate a great amount of data related to location and social activities. These data provide a critical foundation and important basis for location-based personalized recommend services. Therefore, point-of-interest (POI) recommendation services have been extensively developed and applied. The service of POI recommendation is intended to make personalized recommendations of places to mobile users [1]. POI is a location marked by its coordinates as well as related service tags (e.g. restaurants, movie theaters, attractions, etc.). Most POI recommendation algorithms discover users preferences implicitly based on the check-in activities of similar users in LBSNs [2–6]. These algorithms are * Guoqiang Zhou [email protected] 1
College of Computer Science, Nanjing University of Posts and Telecommunication, Nanjing 210003, People’s Republic of China
essentially a collaborative filtering (CF) algorithm [7], which assumes that users with the same preference for certain service are more likely to have the same preference for another category of service. Thus, this method provides users with recommended POIs according to other users check-in data. However, this method does not take into account that the users behavioral habits may change with time and location. For example, most users tend to visit diffe
Data Loading...
