Abstract Pseudo-Relevance Feedback assumes that the top-ranked k documents of the initial retrieval are relevant, and then terms of these documents are used to re-weight the terms of the initial query (add new terms and/or change the weights of existing terms in the query). In this paper, we propose a new approach for query expansion for ad hoc search, by using an absorbing document... Pseudo-Relevance Feedback assumes that the top-ranked k documents of the initial retrieval are relevant, and then terms of these documents are used to re-weight the terms of the initial query (add new terms and/or change the weights of existing terms in the query). In this paper, we propose a new approach for query expansion for ad hoc search, by using an absorbing document which is the cross product of irrelevant documents. This document will be orthogonal to irrelevant ones. We show how this absorbing document can extract better expansion terms from the top-ranked k documents. The experiments show that our approach gives improvements for both collections, TREC-7 and TREC-8, over known models. Read More Read Less

Abstract Among the most powerful tools for knowledge representation, we cite the ontology which allows knowledge structuring and sharing. In order to achieve efficient domain knowledge bases content, the latter has to establish well linked and knowledge between its components. In parallel, data mining techniques are used to discover hidden structures within large databases. In particular, association rules are used to discover co-occurrence relationships... Among the most powerful tools for knowledge representation, we cite the ontology which allows knowledge structuring and sharing. In order to achieve efficient domain knowledge bases content, the latter has to establish well linked and knowledge between its components. In parallel, data mining techniques are used to discover hidden structures within large databases. In particular, association rules are used to discover co-occurrence relationships from past experiences. In this context, we propose, to develop a method to enrich existing ontologies with the identification of novel semantic relations between concepts in order to have a better coverage of the domain knowledge. The enrichment process is realized through discovered association rules. Nevertheless, this technique generates a large number of rules, where some of them, may be evident or already declared in the knowledge base. To this end, the generated association rules are categorized into three main classes: known knowledge, novel knowledge and unexpected rules. We demonstrate the applicability of this method using an existing mammographic ontology and patient’s records. Read More Read Less

Abstract Health information on the Internet is available to help people increase their knowledge and take more responsibility for their health. This study explored how people that vary in severity of health anxiety search for online health information. A cross-sectional research design was employed to evaluate the relationship between online health information seeking and health anxiety. This study surveyed 275 male and 234 female... Health information on the Internet is available to help people increase their knowledge and take more responsibility for their health. This study explored how people that vary in severity of health anxiety search for online health information. A cross-sectional research design was employed to evaluate the relationship between online health information seeking and health anxiety. This study surveyed 275 male and 234 female participants aged 15–67 years living in New Taipei City. The results showed that health anxiety is an effective predictor of health information seeking and that health information seeking is motivated by a health knowledge insufficiency. They also showed a difference between the frequency of online health information seeking and the number of websites visited. In conclusion, online health information seeking is a purposive behavior that can be affected by health anxiety. Read More Read Less