Evaluation of Similarity Measure to Find Coherence

Sentiment Analysis in various applications in diverse domains, plagiarism detection, ambiguity in legal documents, searching an information in Google and translation are few examples of major applications where similarity plays a significant role. Organizing digital documents based on their practical need and usage is need of the hour due to ever-increasing nature of e-resources of documents. We are in the era of transformation from human learning to machine learning. Automatic Organization of Documents into clusters so that intra-cluster possesses high similarity and inter-cluster possess low similarity is the objective of document clustering. Web mining, Information Retrieval, Search Engines, etc., are application of areas of Document Clustering. First, Similarity shall be measured to group documents together. Similarity measurement plays a very important role in organizing documents. In this paper, answers to few questions are pondered and hence few similarity measures are implemented and documents are clustered to realize those answers. Visualization of the clusters reflects satisfactory results.