Author : Mr. Viral Vala1, Dr. Nitika Singhi and Prof. Abhijit Patankar

The descriptive document clustering consists of automatically text classification and generating a descriptive summary for each group. The description should inform a user about the contents of each cluster without further examining the specific instances, allowing the user to quickly search for the relevant clusters. Consistently the mass of data accessible, simply finding the significant data isn’t the main undertaking of programmed content characterization frameworks. Rather the automatic text classification systems are supposed to retrieve the relevant information as well as organize according to its degree of relevancy with the given query. The main problem in organizing is to classify which documents are relevant and which are irrelevant. The Automated content grouping consists of automatically organizing clustered data. We propose a programmed strategy for content characterization using machine learning based on the disambiguation of the meaning of the word we utilize the word net word installing calculation to dispose of the equivocalness of words with the goal that each word is supplanted by its importance in the setting. The nearest precursors of the faculties of all the intact words in a given record are chosen as classes for the predefined report.

Keywords: Document Clustering, Feature Selection, Model Selection, Machine Learning, Semantic Analysis