Topic-based clustering of news articles

ABSTRACT

Recent years have witnessed an explosion in the availability of news articles on the World Wide Web. Although search-engines' algorithms have made it easier to locate these documents, they still require considerable effort on the part of the user since most search engine algorithms look for keywords and do not take the contents of the entire article into context. We propose a system that clusters articles based on their topics. More specifically, we have focused on applying text mining methods to help solve the problems faced by a media organization or public relations department.

REFERENCES

• 1: Chris Clifton , Robert Cooley, TopCat: Data Mining for Topic Identification in a Text Corpus, Proceedings of the Third European Conference on Principles of Data Mining and Knowledge Discovery, p.174-183, September 15-18, 1999
• 2: M. Porter, "An algorithm for suffix stripping," Automated Library and Information Systems, vol. 14, no. 3, pp. 130--137, 1980.
• 3: ERIC Database: Searching Assistant--Stopwords. <u>http://www.askeric.org/Eric/Help/stop.shtml</u>

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

Keywords:
Jaccard coefficient, article clustering, clustering, data mining, stemming, text mining