ENHANCING THE PERFORMANCE OF CLUSTER BASED TEXT SUMMARIZATION USING SUPPORT VECTOR MACHINE

M. S Patil, M. S. Bewoor, S. H. Patil

Abstract: Technology is evolving day by day and this increase in technology is nothing but is the efforts to reduce human work and to have systems as automatic as possible. Same thing is true in terms of existence of digital information. Due to enormous increase in the use of internet, there is striking increase in the digital information. This digital information is characterized by different form of information, same information in different form, unrelated information and also there is lot of redundant information. Another next important thing to note is that most of the time we require textual information. To search or retrieve small information one has to go through thousands of documents, read all the retrieved documents irrespective whether they contain useful information or no. It becomes very difficult to read all the retrieved documents and prepare exact summary out of it within time. Besides this, many times retrieved information is repeated in almost many documents. This leads to research in the area of text mining. Text summarization is one of the challenging tasks in the field of text mining

Keywords: Entropy, FCM, Purity, SVM

DOI: https://doi.org/10.15623/ijret.2014.0312007