Point Of Interest Recommendation In LBSN:Travelling To A New Geographical Region

Currently,recommender systems in location based social network(LBSN)mainly takes advantage of social and geographical influence in making personalized Points-ofinterests(POI)recommendation.The social influence is obtained from social network friends or similar users based on matching visit history,and geographical influence is obtained from the geographical footprints users' leave when they check-in at different(POIs).However,this approach may fall short when a user moves to a new district or city where they have little or no activity history and social network friend information from which the system can infer their preferences in order make a personalized recommendation.Thus,a need to reconsider how we model the factors influencing a user's preferences in a new geographical regions in order to make personalized and relevant recommendation.A POI in LBSNs is semantically enriched with annotations such as place categories,tags,tips or user reviews which implies knowledge about the nature of the place as well as a visiting person's interests.This provides us with opportunities to better understand the patterns in users' interests and activities by exploiting the annotations which will continue to be useful even when a user moves to unfamiliar places.In this research,we propose a location aware POI recommendation system that models user preferences mainly based on;user reviews-through which users' express their sentiments on a particular POI visited hence generally expressing the properties they value or not from certain types of POIs and categories of POIs-which shows the nature of activities that a user finds interesting.Using this information from users' location history,we predict user ratings by harnessing the information present in review text as well as consider social influence from similar user set formed based on matching category preferences and similar reviews.We use real datasets partitioned by city provided by Yelp a popular LBSN,to compare the accuracy of our proposed method against some baseline POI recommendation algorithms.Experimental results show that our algorithm achieves a better accuracy.