Objectives: The main objectives of this methodology are to improve the performance of the web crawlers by retrieving the web pages based on the user queries. And also this work aims to construct the user interest ontology in terms of the user interest features by extracting the syntactic and semantic relationship exists among them.
Methods: The semantic meaning extraction for the user interest terms are proposed in this work. This is done with the help word net toolkit which aims to retrieve the concept and meaning of each and every word. Then the user interest ontology is constructed by deriving the concept relation present among the user submitted terms and the documents by calculating the relatedness and the similarity present among them with the help of tf- IDF score and the semantic relation. Finally formal concept analysis is used to represent the terms of the user interest features in the hierarchical form.
Results: The experimental tests were conducted after implementation of the proposed methodology in order to prove the effectiveness of the algorithm. This is done by comparing it with the existing work in terms of precision and recall performance measures. The experimental tests conducted were proves that the proposed methodology is improved in terms of both precision and recall measure.
Conclusion: The findings of this work demonstrate that the proposed methodology provides the user interest ontology construction and retrieve the user interested seed URL in the effective manner.
Keywords
