ABSTRACT:

All clustering methods have to assume some cluster relationship among the information objects that they are applied on. Similarity between a combine of objects will be defined either explicitly or implicitly. In this paper, we have a tendency to introduce a novel multi-viewpoint primarily based similarity measure and 2 connected clustering methods. The major distinction between a traditional dissimilarity/similarity live and ours is that the former uses solely a single viewpoint, that is that the origin, while the latter utilizes several different viewpoints, that are objects assumed to not be in the same cluster with the 2 objects being measured. Using multiple viewpoints, additional informative assessment of similarity could be achieved. Theoretical analysis and empirical study are conducted to support this claim. 2 criterion functions for document clustering are proposed based mostly on this new measure. We tend to compare them with many well-known clustering algorithms that use other popular similarity measures on numerous document collections to verify the advantages of our proposal.