Keyword Extraction using Clustering and Semantic Analysis

Dr. Mohamed H. Haggag, Dr.Amal Abutabl, Ahmed Basil

Abstract: Keywords are list of significant words or terms that best present the document context in brief and relate to the textual context. Extraction models are categorized into either statistical, linguistic, machine learning or a combination of these approaches. This paper introduces a model for extracting keywords by making words pairs and clustering these pairs based on the Semantic similarity that will be provided by using lesk algorithm and (WordNet), a lexical database for the English language. The model also used a statistical method to ensure clusters cohesion and provide more reliable result, because the final keywords will be selected from these clusters. This paper also show three other basic approaches to extract keywords, these approaches will be used to measure the efficient of the main approach. The proposed model showed enhanced over the three other approaches in both precision and recall.

Keywords: extraction, semantic analysis, wordnet

How to Cite?: Dr. Mohamed H. Haggag, Dr.Amal Abutabl, Ahmed Basil, "Keyword Extraction using Clustering and Semantic Analysis", Volume 3 Issue 11, November 2014, International Journal of Science and Research (IJSR), Pages: 1128-1132, https://www.ijsr.net/getabstract.php?paperid=OCT141022, DOI: https://dx.doi.org/10.21275/OCT141022