Title: Natural language processing-based e-news recommender system using information extraction and domain clustering
Authors: S. Sowmya Kamath; Monisha Kanakaraj
Addresses: Department of Information Technology, National Institute of Technology Karnataka, Surathkal, Srinivas Nagar, P.O., Mangalore 575025, India ' Department of Information Technology, National Institute of Technology Karnataka, Surathkal, Srinivas Nagar, P.O., Mangalore 575025, India
Abstract: In general, most news search engines retrieve news articles based on the keywords present in the submitted search query. As most e-newspapers deal with a similar set of news articles on a particular day, clustering of these articles based on similarity of the news content will give better user experience, while recommending articles to users. There are several clustering algorithms that can be used to cluster data based on a basic bag-of-words approach. In this paper, an intelligent news search engine that identifies similar news articles available from multiple sources on a given day, using a semantics-based enhanced bag-of-words approach to leverage the efficiency of search is proposed. Natural language processing techniques were used to identify articles dealing with the same news and serve a user query with summarised news from all sources. Experimental results showed that the proposed approach performed well and retrieved meaningful results, and an improvement of 4% in recall and 5% in precision was observed over keywords-based bag-of-words model.
Keywords: information retrieval; recommender systems; document clustering; semantics; natural language processing; NLP e-news; electronic newspapers; online news; information extraction; news content clustering; article clustering; news articles; clustering algorithms; news search engines; intelligent search engines.
International Journal of Image Mining, 2015 Vol.1 No.1, pp.112 - 125
Received: 23 Mar 2015
Accepted: 19 Apr 2015
Published online: 23 Jun 2015 *