A Graph-Based Model for Keyword Extraction and Tagging of Research Documents

This paper presents an unsupervised approach for extracting keywords from documents and tagging of research documents with the help of extracted keywords. Keywords are useful for checking the similarity between two documents. This will help us to correctly cluster the related documents with respect to their domains. In this paper, we are describing how research papers are clustered using keywords. A report is generated with respect to the author's contribution in different domains. The system uses Keyword Extraction using Collective Node Weight for extraction of keywords, Node-Edge Rank for ranking Keywords and WordNet Similarity Measurement for tagging of Research papers.