Document Object Mapping and Clustering Using Semantic Indexing Process

Abstract

Document clustering aims to automatically group related documents into clusters. It is on of the most important tasks in machine learning and artificial intelligence and has received much attention in recent years During this framework, the documents are projected into a low-dimensional semantic area during which the correlations between the documents within the native patches are maximized whereas the correlations between the documents outside these patches are minimized simultaneously. Since the intrinsic geometrical structure of the document area is usually embedded within the similarities between the documents, correlation as a similarity live is additional appropriate for detecting the intrinsic geometrical structure of the document area than Euclidean distance. Consequently, the proposed CPI technique will effectively discover the intrinsic structures embedded in high-dimensional document area. The effectiveness of the new technique is demonstrated by in depth experiments conducted on varied information sets and by comparison with existing document clustering strategies