Optimization and Application of OPTICS Algorithm on Text Clustering

Abstract

Text clustering is of great importance in data mining, information fusion, artificial intelligence and some other fields. There are many methods in literatures that can be used to classify text. Most of them require some parameters, such as the number of categories, which should be assigned in advance or estimated in classifying process. However, it is difficult to determine these quantities in text clustering. OPTICS is one of clustering algorithms that does not depend on the preset number of categories. In this paper, we introduce an optimization method based on OPTICS to simplify the cluster identification process and improve classification accuracy, and then apply it on text clustering. We also test it on a widely used text corpus. Results show that the proposed method can weaken the influence of data noise and bring more precision to text clustering.

A Systematic Comparative Analysis of Clustering Techniques

“…The priority is given to high density clusters [34]. It stores two types of information about the data points present in the clusters formed: core distance and reachability distance [35].…”