To search, Click below search items.


All Published Papers Search Service


Evaluation of a Text Document Clustering Approach based on Particle Swarm Optimization


Stuti Karol, Veenu Mangat


Vol. 13  No. 7  pp. 130-143


Fast and high-quality document clustering algorithms play an extremely important role in document clustering for effective navigation, summarization, and organization of information. The documents to be clustered can be web news articles, abstracts of research papers etc. This paper suggests two techniques for efficient document clustering; these suggested techniques involving the application of soft computing approach as an intelligent hybrid PSO based algorithm. The two approaches are partitioning clustering algorithms Fuzzy C-Means (FCM) and K-Means each hybridized with Particle Swarm Optimization (PSO). The performance of these hybrid algorithms has been evaluated against traditional partitioning clustering techniques (K-Means and Fuzzy C Means) without hybridization. The hybrid algorithms when compared with traditional techniques (without hybridization) on two benchmark text document datasets provide better quality document clusters in terms of two standard document clustering evaluation measures; Entropy and F-Measure.


Clustering analysis, Optimization, Swarm Intelligence, K-Means Clustering, Fuzzy C-Means Clustering, Particle Swarm Optimization, Text Document Clustering