{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T11:04:06Z","timestamp":1778670246643,"version":"3.51.4"},"reference-count":7,"publisher":"World Scientific Pub Co Pte Ltd","issue":"01","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Info. Know. Mgmt."],"published-print":{"date-parts":[[2008,3]]},"abstract":"<jats:p> Similarity is an important and widely used concept in many applications such as Document Summarisation, Question Answering, Information Retrieval, Document Clustering and Categorisation. This paper presents a comparison of various similarity measures in comparing the content of text documents. We have attempted to find the best measure suited for finding the document similarity for newspaper reports. <\/jats:p>","DOI":"10.1142\/s0219649208001889","type":"journal-article","created":{"date-parts":[[2008,4,28]],"date-time":"2008-04-28T07:04:25Z","timestamp":1209366265000},"page":"1-8","source":"Crossref","is-referenced-by-count":14,"title":["A Comparison of Similarity Measures for Text Documents"],"prefix":"10.1142","volume":"07","author":[{"given":"Shanmugasundaram","family":"Hariharan","sequence":"first","affiliation":[{"name":"Faculty of Information Technology, B.S.A. Crescent Engineering College Chennai, Tamilnadu, India"}]},{"given":"Rengaramanujam","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Engineering, B.S.A. Crescent Engineering College Chennai, Tamilnadu, India"}]}],"member":"219","published-online":{"date-parts":[[2011,11,21]]},"reference":[{"key":"rf2","author":"Bani-Ahmad S.","journal-title":"Bulletin of the IEEE Computer Society Technical Committee on Data Engineering"},{"key":"rf6","doi-asserted-by":"publisher","DOI":"10.1147\/rd.22.0159"},{"key":"rf7","doi-asserted-by":"publisher","DOI":"10.1108\/eb046814"},{"key":"rf8","volume-title":"Database Management Systems","author":"Ramakrishnan R.","year":"1999"},{"key":"rf9","volume-title":"The Smart Retrieval System \u2014 Experiments in Automatic Document Processing","author":"Salton G.","year":"1971"},{"key":"rf10","volume-title":"Recognizing Text Similarity","author":"Uzuner O.","year":"2004"},{"key":"rf12","volume-title":"Human Behaviour and the Principle of Least Effort","author":"Zipf H. P.","year":"1949"}],"container-title":["Journal of Information &amp; Knowledge Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.worldscientific.com\/doi\/pdf\/10.1142\/S0219649208001889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,6]],"date-time":"2019-08-06T23:27:55Z","timestamp":1565134075000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.worldscientific.com\/doi\/abs\/10.1142\/S0219649208001889"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,3]]},"references-count":7,"journal-issue":{"issue":"01","published-online":{"date-parts":[[2011,11,21]]},"published-print":{"date-parts":[[2008,3]]}},"alternative-id":["10.1142\/S0219649208001889"],"URL":"https:\/\/doi.org\/10.1142\/s0219649208001889","relation":{},"ISSN":["0219-6492","1793-6926"],"issn-type":[{"value":"0219-6492","type":"print"},{"value":"1793-6926","type":"electronic"}],"subject":[],"published":{"date-parts":[[2008,3]]}}}