A Clustering Method for Web Mining Based on Probabilistic Latent Semantic Indexing

摘要

Exploring an intranet or internet database enables us to discover useful knowledge. In this process, a search engine plays a pivotal role. To this end, various search engines have been proposed to heighten information accuracy by exploiting key content relations in semantic web resources. But a general-purpose search engine always includes useless or irrelevant web pages in the search results. The next generation of web architecture, known as Semantic Web, can build a layered architecture to possibly mitigate this deficiency by decreasing the noisy data in a searched result. The objective of this paper is to propose a Probabilistic Latent Semantic Indexing (PLSI) method used in semantic web search engines. The method can better return appropriate information for user queries; in particular, a novel ranking strategy is provided to measure the relevance score of an annotated set of web results by considering user queries, data annotation, and the underlying ontology.