Semantic manipulation of user’s queries and modeling the health and nutrition preferences

Abstract

People depend on popular search engines to look for the desired health and nutrition information. Many search engines cannot semantically interpret, enrich the user’s natural language queries easily and hence do not retrieve the personalized information that fits the user’s needs. One reason for retrieving irrelevant information is the fact that people have different preferences where each one likes and dislikes certain types of food. In addition, some people have specific health conditions that restrict their food choices and encourage them to take other foods. Moreover, the cultures, where people live in, influence food choices while the search engines are not aware of these cultural habits. Therefore, it will be helpful to develop a system that semantically manipulates user’s queries and models the user’s preferences to retrieve personalized health and food information. In this paper, we harness semantic Web technology to capture user’s preferences, construct a nutritional and health-oriented user’s profile, model the user’s preferences and use them to organize the related knowledge so that users can retrieve personalized health and food information. We present an approach that uses the personalization techniques based on integrated domain ontologies, pre-constructed by domain experts, to retrieve relevant food and health information that is consistent with people’s needs. We implemented the system, and the empirical results show high precision and recall with a superior user’s satisfaction.