{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T21:52:37Z","timestamp":1759960357731,"version":"3.32.0"},"publisher-location":"Berlin, Heidelberg","reference-count":20,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540370338"},{"type":"electronic","value":"9783540370352"}],"license":[{"start":{"date-parts":[[2006,1,1]],"date-time":"2006-01-01T00:00:00Z","timestamp":1136073600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11811220_19","type":"book-chapter","created":{"date-parts":[[2006,7,24]],"date-time":"2006-07-24T12:40:48Z","timestamp":1153744848000},"page":"215-228","source":"Crossref","is-referenced-by-count":34,"title":["Using Word Clusters to Detect Similar Web Documents"],"prefix":"10.1007","author":[{"given":"Jonathan","family":"Koberstein","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiu-Kai","family":"Ng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"19_CR1","unstructured":"Baeza-Yates, R., Ribeiro-Neto, B.: Modern Information Retrieval (1999)"},{"key":"19_CR2","unstructured":"http:\/\/packetstormsecurity.nl\/Crackers\/bigdict.gz"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Brin, S., Davis, J., Garcia-Molina, H.: Copy Detection Mechanisms for Digital Documents. In: Proc. of the ACM SIGMOD, pp. 398\u2013409 (1995)","DOI":"10.1145\/568271.223855"},{"key":"19_CR4","volume-title":"Bayesian Statistical Modelling","author":"P. Congdon","year":"2001","unstructured":"Congdon, P.: Bayesian Statistical Modelling. Wiley, Chichester (2001)"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Cooper, J., Coden, A., Brown, E.: Detecting Similar Documents Using Salient Terms. In: Proc. of CIKM 2002, pp. 245\u2013251 (2002)","DOI":"10.1145\/584834.584835"},{"key":"19_CR6","unstructured":"http:\/\/prdownloads.sourceforge.net\/wordlist\/12dicts-4.0.zip"},{"key":"19_CR7","unstructured":"http:\/\/www.luziusschneider.com\/Speller\/ISpEnFrGe.exe"},{"key":"19_CR8","unstructured":"Manber, U.: Finding Similar Files in Large File System. In: USENIX Winter Technical Conf. (1994)"},{"key":"19_CR9","unstructured":"Nevin, H.: Scalable Document Fingerprinting. In: Proc. of the 2nd USENIX Workshop on Electronic Commerce, pp. 191\u2013200 (1996)"},{"key":"19_CR10","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"J. Pearl","year":"1988","unstructured":"Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)"},{"issue":"4","key":"19_CR11","first-page":"247","volume":"2","author":"A.R. Pereira","year":"2004","unstructured":"Pereira, A.R., Ziviani, N.: Retrieving Similar Documents from the Web. Journal of Web Engineering\u00a02(4), 247\u2013261 (2004)","journal-title":"Journal of Web Engineering"},{"issue":"3","key":"19_CR12","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1108\/eb046814","volume":"14","author":"M. Porter","year":"1980","unstructured":"Porter, M.: An Algorithm for Suffix Stripping. Program\u00a014(3), 130\u2013137 (1980)","journal-title":"Program"},{"key":"19_CR13","doi-asserted-by":"crossref","unstructured":"Rabelo, J., Silva, E., Fernandes, F., Meira, S., Barros, F.: ActiveSearch: An Agent for Suggesting Similar Documents Based on User\u2019s Preferences. In: Proc. of the Intl. Conf. on Systems, Men & Cybernetics, pp. 549\u2013554 (2001)","DOI":"10.1109\/ICSMC.2001.969871"},{"key":"19_CR14","unstructured":"http:\/\/www.ime.usp.br\/~yoshi\/mac324\/projecto\/dicas\/entras\/words"},{"issue":"3","key":"19_CR15","first-page":"267","volume":"19","author":"I. Ruthven","year":"2002","unstructured":"Ruthven, I., Lalmas, M.: Experimenting on Dempster-Shafer\u2019s Theory of Evidence in Information Retrieval. JIIS\u00a019(3), 267\u2013302 (2002)","journal-title":"JIIS"},{"key":"19_CR16","unstructured":"Shivakumar, N., Garcia-Molina, H.: SCAM: A Copy Detection Mechanism for Digital Documents. D-Lib Magazine (1995), http:\/\/www.dlib.org"},{"key":"19_CR17","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Wikipedia:Database_download"},{"key":"19_CR18","unstructured":"http:\/\/en.wikipedia.org\/wiki\/Wikipedia:Overview_FAQ (February 03, 2006)"},{"key":"19_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1007\/11539506_70","volume-title":"Fuzzy Systems and Knowledge Discovery","author":"R. Yerra","year":"2005","unstructured":"Yerra, R., Ng, Y.-K.: A Sentence-Based Copy Detection Approach for Web Documents. In: Wang, L., Jin, Y. (eds.) FSKD 2005. LNCS, vol.\u00a03613, pp. 557\u2013570. Springer, Heidelberg (2005)"},{"key":"19_CR20","unstructured":"Yu, C., Liu, K., Wu, W., Meng, W., Rishe, N.: Finding the Most Similar Documents Across Multiple Text Databases. In: Proc. of the IEEE Forum on Research and Technology Advances in Digital Libraries, pp. 150\u2013162 (1999)"}],"container-title":["Lecture Notes in Computer Science","Knowledge Science, Engineering and Management"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11811220_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T01:39:02Z","timestamp":1736473142000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11811220_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540370338","9783540370352"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/11811220_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}