A hybrid approach for text clustering

This paper deals with automatic clustering algorithm, which partitions a many of objects to get smaller sets (clusters). Where objects of the one set are related to each other rather than to those in the other sets. The number of clusters in automatic clustering don’t given priori, they determinates automatically, the number resulted of clusters exact closed to the numbers of the real dataset structure. This paper represents a stimulus for the current study to introduce an algorithm that automatically finds the number of clusters based on distance among vertices. The study is based on the hypothesis that the proposed algorithm is able to efficiently find the clustering partitions for the whole dataset.