A Survey on Text Based Clustering

Clustering is the main technique for data analysis and it deals with the organisation of a set of objects in a multidimensional space into cohesive groups called clusters. Every cluster contains closely related objects and has very dissimilar objects in other clusters. Cluster analysis aims at discovering the objects with same behaviour in a collection. Thus, if an object satisfies a rule, the all objects that are similar to that object will satisfy the same rule. With this functionality the hidden similarity, relationship and other concepts can be predicted with respect to the cluster of objects. In this work, we present a survey on text based mining.