An Improved Automatic Keyword Extraction using Graph based Modeling

Automatic extraction of key terms from a document is indispensable in the digital era to sum up the documents. For instance, instead of reviewing the full document from beginning to end, some of the author's keywords somewhat explain the discussions of the documents. However, the author's keywords are not adequate to recognize the whole idea of the document. Hence the necessity of automatic term extraction methods is essential. The automatic extraction approaches is mostly classified on some techniques such as Natural Language Processing, Statistical approaches, Graph Based approaches, Natural Inspired algorithmic approaches, etc. Even though there are abundant approaches accessible, the exact automatic keyword extraction is a most important
dare in areas, which reveals around documents. In this paper, a study of Keyword extraction among Graph based approach is done. In the Graph based approach, the documents are robotically formed as graphs by applying centrality measures during the keyword extraction process. The results of centrality measures were compared and analyzed.