Personalized location aware recommendation system

Abstract

A Personalized location aware recommendation system has been designed and evaluated in this paper. The idea is to infer user's preferences and thus to recommend nearby locations such as hospitals, food courts, shopping and so on. User's current search contexts are rarely considered by the well known location recommendation system named FOURSQUARE (https://foursquare.com/). Thus, the paper enhances the system by incorporating personalization features to provide personalized location suggestions based on users' preferences. Typical recommender systems make use of community opinions/reviews to help users identify useful items from a large search space e.g., Search for nearby health care centre or hospital specialized for heart problems, restaurant specialized for vegetarian, etc. The technique used by current systems is collaborative filtering algorithm which analyzes reviews from group of people to find correlations of similar users and to suggest top items to a querying user. The limitation with considering group opinions is that individual user preferences are not leveraged. Thus the proposed system analyzes location aware reviews in order to understand the community user experiences and further it is matched with a specific user search preference to suggest preferable locations for meeting their goal especially when they are in a new place.