Trust Level Computation Based On Time-Aware Social Interactions For Recommending Medical Tourism Destinations

Social trust-based recommendation systems are currently based on the computation of the level of trust in users' interactions or on a combination of trust and similarity scores while generating recommendations. In this research paper, we propose a framework for a recommender system that is based on users' preferences on the one hand and on the opinions of their trusted friends on the other hand to return recommendations. A Trusted Friends' computation technique is developed to identify socially trusted friends in Facebook We have, therefore, showed the significance of the time of the interactions between users for a better detection of trusted friends. Afterwards, we have used this method to build an ontology-based medical tourism recommender system as a smart e-tourism tool able to recommend items based on the tendencies of the users and of their trusted friends in social network We have applied our tourism recommender system for the support of the customers of medical tourism services in Tunisia, we have implemented the system to evaluate the quality of the recommendations it generates and to prove its importance in improving the medical tourism domain, and we proved using an objective statistical method that traditional recommender systems can be enhanced through the time-aware incorporation of data from social networks; such as the preferences of the user and his trusted friends.