Natural language processing-based e-news recommender system using information extraction and domain clustering
by S. Sowmya Kamath; Monisha Kanakaraj
International Journal of Image Mining (IJIM), Vol. 1, No. 1, 2015

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.

Online publication date: Wed, 24-Jun-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Image Mining (IJIM):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email