Search

Abstract: The vision of semantic Web is to have a Web of data instead of Web of documents in a form that can be processed by machines. This vision could be achieved in the existing Web using semantic annotation. Due to exponential growth and huge size of the Web sources, there is a need to have a fast and automatic semantic annotation of Web documents. Arabic language has received less attention in semantic Web research compared to Latin languages especially in the field of semantic annotation. In this paper, we present an automatic annotation tool that supports the semantic annotation of Arabic language Web documents. The tool takes a URL of Web document and the corresponding ontology then produces an external annotation of the Web document using Resource Description Framework (RDF) language. The annotation tool's output could be used by semantic search engines to achieve higher recall and precision. To evaluate the performance of the tool, three domain ontologies of food, nutrition and health were used with manually annotated documents related to those domains. The initial results show a promising performance which will support the research in the semantic Web with respect to Arabic language. [Copyright &y& Elsevier]

Abstract: People depend on popular search engines, like Google and Yahoo, to retrieve the desired information from the Web. Searching for the right food, to eat, is an example of the frequent queries on the Web where people do not find relevant information easily. One reason for this un-satisfaction is the fact that many people have personal preferences where each one likes and dislikes certain food. Also, some people have specific health conditions that restrict their food choices and encourage them to take other food. In addition, the cultures, where people live in, influence food choices and varieties. Therefore, it will be helpful to develop a framework that provides food recommendation, what to take and what to avoid, increasing the advantages and reducing the risks especially for people who have long term diseases such as diabetes and high-blood-pressure. Since health and nutrition information is critical and hence people need to get precise information from trusted sources. Furthermore, transforming the implied knowledge about health and nutrition into structured data is challenging, so developing a framework that semantically manipulate the health and nutrition information is becoming an increasingly important research topic. In this paper, we harness semantic Web and ontology engineering technologies to analyze user's preferences, construct a nutritional and health oriented user's profile, and use the profile to organize the related knowledge so that users can make smarter food and health inquires. We present a semantic framework that uses the personalization techniques based on integrated domain ontologies, pre-constructed by domain experts, to recommend the relevant food that is consistent with people's needs. The empirical evaluation of the proposed framework shows promising results for recommending the relevant food information with a superior user's satisfaction. [Copyright &y& Elsevier]