Social Semantic Retrieval and Ranking of eResources

Abstract

World Wide Web provides a huge collection of learning resources. However, as traditional retrieval algorithms lack the use of semantics to retrieve relevant documents, voluminous information is retrieved most of which may be irrelevant to the posted query. Due to which the learning process of a learner is slowed down. Hence, a need is felt to develop a retrieval and ranking method that produces semantically relevant web resources with information need. For this reason, the paper proposes semantically relevant retrieval and ranking of web resources that uses top N resource links returned from a search engine as seed, domain ontologies to compute semantic relevance, and data from Social Bookmarking System (SBS) to retrieve additional semantically relevant resources. Finally all retrieved resources are ranked according to the query relevancy using Vector Space Model (VSM). The proposed approach presented in this paper is elucidated in three parts: (i) a method that expands a posted query using semantic relevance by using ontologies, (ii) an algorithm to retrieve semantically relevant web resources by simulating human cognition using SBS, and (iii) a new approach to compute social semantic ranking of retrieved web resources. Thus it utilizes collective advantages of Social Bookmark Tagging System and Semantic technologies. Improvement in results obtained by the proposed approach in contrast to the existing results retrieved by search engine is apparent from empirical evaluation.