A Rough Concept Recognition Approach for Information Retrieval Based on Latent Semantic Analysis

This paper presents an information retrieval approach which uses a rough concept clustering in conjunction with Latent Semantic Analysis(LSA) to provide better document retrieval results matched to queries. The conceptual context defined in this article can be local, so no domain expert has to be involved in this approach. Our experiment consists of word clustering by similarity and rough concept recognition, associated to a basic LSA retrieval system. Our information retrieval process is illustrated through our experimentation model and results are compared in two different aspects. Experiment results show that retrieval performance benefit can be gained from this approach and further performance benefits can also be obtained according to the further work, which needs researching about parameter settings and algorithm development.