Efficient Information Retrieval Using Document Clustering

Abstract

Locating interesting information is one of the most important tasks in Information Retrieval (IR). The different IR
systems emphasize different query features when determining relevance and therefore retrieved from different sets of documents.
Clustering is an approach to improve the effectiveness of IR. In clustering, documents are clustered either before or after retrieval.
The motivation of this paper is to explain the need of clustering in retrieving efficient information that closely associates
documents which are relevant to the same query. Here IR framework has been defined which consists of four steps (1) IR system
(2) similarity measure (3) document clustering and (4) ranking of clusters. Furthermore, we present the short comings of cluster
algorithms based on the various facets of their features and functionality. Finally based on the review of the different approaches
we conclude that although clustering has been a topic for scientific community for three decades, there are still many open issues
that call for more research.

Keywords: Information Retrieval, IR System, Document Clustering, Similarity measure, Ranking