Research on Personalized Tourism Attractions Recommendation Model Based on User Social Influence

With the rapid development of social networks, location-based social network gradually rise. In order to retrieve user most prefer attractions from a large number of tourism information, location-based personalized recommendation technology has been widely concerned in academic and industry. For the solving techniques problems such as data sparsity and cold-start existed in personalized recommendation system, this paper proposes a personalized location recommendation model-SocInflu, which combines user collaborative filtering technology with social networks factor. This method fully exploits social relations and trust relations between users and recommends users most interest attractions by the means of social influence and position information between user and tourism attractions. Experimental results on real data sets demonstrate the feasibility and effectiveness of the proposed model. Compared with the existing recommendation algorithm, it has higher prediction accuracy.