{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T13:19:09Z","timestamp":1760707149778},"reference-count":27,"publisher":"Elsevier BV","issue":"3-4","license":[{"start":{"date-parts":[[2003,10,1]],"date-time":"2003-10-01T00:00:00Z","timestamp":1064966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information Sciences"],"published-print":{"date-parts":[[2003,10]]},"DOI":"10.1016\/s0020-0255(03)00169-5","type":"journal-article","created":{"date-parts":[[2003,7,31]],"date-time":"2003-07-31T23:44:52Z","timestamp":1059695092000},"page":"181-197","source":"Crossref","is-referenced-by-count":33,"title":["Category cluster discovery from distributed WWW directories"],"prefix":"10.1016","volume":"155","author":[{"given":"Mei-Ling","family":"Shyu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Choochart","family":"Haruechaiyasak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shu-Ching","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/S0020-0255(03)00169-5_BIB1","series-title":"Current Trends in Artificial Intelligence","first-page":"412","article-title":"Knowledge acquisition via knowledge integration","author":"Brazdil","year":"1990"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB2","doi-asserted-by":"crossref","unstructured":"A. Broder, S. Glassman, M. Manasse, G. Zweig, Syntactic clustering of the Web, in: Proc. of the Sixth Int. WWW Conf., 1997, pp. 391\u2013404","DOI":"10.1016\/S0169-7552(97)00031-7"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB3","doi-asserted-by":"crossref","unstructured":"S. Chakrabarti, B. Dom, P. Indyk, Enhanced hypertext categorization using hyperlinks, in: Proc. of the ACM SIGMOD Int. Conf. on Management of Data, 1998, pp. 307\u2013318","DOI":"10.1145\/276304.276332"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB4","doi-asserted-by":"crossref","unstructured":"R. Cooley, B. Mobasher, J. Srivastava, Web mining: information and pattern discovery on the World Wide Web, in: Proc. of the 9th IEEE Int. Conf. on Tools with Artificial Intelligence, 1997, pp. 558\u2013567","DOI":"10.1109\/TAI.1997.632303"},{"issue":"2","key":"10.1016\/S0020-0255(03)00169-5_BIB5","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1145\/565117.565124","article-title":"Cluster validity methods: part I","volume":"31","author":"Halkidi","year":"2002","journal-title":"SIGMOD Record"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB6","doi-asserted-by":"crossref","unstructured":"C. Haruechaiyasak, M.-L. Shyu, S.-C. Chen, X. Li, Web document classification based on fuzzy association, in: Proc. of the 26th IEEE Int. Computer Software and Applications Conf., 2002, pp. 487\u2013492","DOI":"10.1109\/CMPSAC.2002.1045052"},{"issue":"3","key":"10.1016\/S0020-0255(03)00169-5_BIB7","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1142\/S1469026802000609","article-title":"Identifying topics for Web documents through fuzzy association learning","volume":"2","author":"Haruechaiyasak","year":"2002","journal-title":"Int. J. Comput. Intell. Appl. (IJCIA)"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB8","series-title":"Finding Groups in Data: An Introduction to Cluster Analysis","author":"Kaufman","year":"1990"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB9","doi-asserted-by":"crossref","unstructured":"D. Lewis, Naive Bayes at forty: the independence assumption in information retrieval, in: Proc. of European Conf. on Machine Learning, 1998, pp. 4\u201315","DOI":"10.1007\/BFb0026666"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB10","unstructured":"A. McCallum, K. Nigam, A comparison of event models for Naive Bayes text classification, in: Proc. of the AAAI-98 Workshop on Learning for Text Categorization, 1998, pp. 41\u201348"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB11","unstructured":"H.S. Pinto, A.G. Perez, J.P. Martins, Some issues on ontology integration, in: Proc. of IJCAI Workshop on Ontologies and Problem Solving Methods: Lessons Learned and Future Trends, 1999, pp. 7.1\u20137.12"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB12","unstructured":"J. Pitkow, P. Pirolli, Mining longest repeating subsequences to predict World Wide Web surfing, in: Proc. USENIX Symp. on Internet Technologies and Systems, 1999, pp. 139\u2013150"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB13","series-title":"Information Retrieval: Data Structures & Algorithms","first-page":"419","article-title":"Clustering algorithms","author":"Rasmussen","year":"1992"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB14","unstructured":"G. Salton (Ed.), The SMART Retrieval System: Experiments in Automatic Document Processing, Prentice-Hall Series in Automatic Computation, Englewood Cliffs, NJ, 1971"},{"issue":"11","key":"10.1016\/S0020-0255(03)00169-5_BIB15","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1145\/361219.361220","article-title":"A vector-space model for information retrieval","volume":"18","author":"Salton","year":"1975","journal-title":"Commun. ACM"},{"issue":"5","key":"10.1016\/S0020-0255(03)00169-5_BIB16","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1016\/0306-4573(88)90021-0","article-title":"Term weighting approaches in automatic text retrieval","volume":"24","author":"Salton","year":"1988","journal-title":"Inform. Process. Manage."},{"key":"10.1016\/S0020-0255(03)00169-5_BIB17","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"Bell Syst. Tech. J."},{"key":"10.1016\/S0020-0255(03)00169-5_BIB18","unstructured":"M.-L. Shyu, S.-C. Chen, C. Haruechaiyasak, Mining user access behavior on the WWW, in: IEEE Int. Conf. on Syst., Man, and Cybernet., 2001, pp. 1717\u20131722"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB19","unstructured":"M.-L. Shyu, S.-C. Chen, C. Haruechaiyasak, C.-M. Shu, S.-T. Li, Disjoint Web document clustering and management in electronic commerce, in: Seventh Int. Conf. on Distr. Multi. Syst., 2001, pp. 494\u2013497"},{"issue":"5","key":"10.1016\/S0020-0255(03)00169-5_BIB20","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1145\/505696.505701","article-title":"A survey of Web caching schemes for the Internet","volume":"29","author":"Wang","year":"1999","journal-title":"ACM Comp. Comm. Rev."},{"key":"10.1016\/S0020-0255(03)00169-5_BIB21","doi-asserted-by":"crossref","unstructured":"Y. Yang, A study on thresholding strategies for text categorization, in: Proc. of the 24th ACM Int. Conf. on Research and Development in Information Retrieval, 2001, pp. 137\u2013145","DOI":"10.1145\/383952.383975"},{"issue":"1\/2","key":"10.1016\/S0020-0255(03)00169-5_BIB22","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1023\/A:1009982220290","article-title":"An evaluation of statistical approaches to text categorization","volume":"1","author":"Yang","year":"1999","journal-title":"J. Inform. Retrieval"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB23","unstructured":"Y. Yang, J.P. Pedersen, A comparative study on feature selection in text categorization, in: Proc. of the Fourteenth Int. Conf. on Machine Learning, 1997, pp. 412\u2013420"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB24","doi-asserted-by":"crossref","unstructured":"O. Zamir, O. Etzioni, Web document clustering: a feasibility demonstration, in: Proc. of the 21st Int. ACM SIGIR Conf. on Research and Development in Information Retrieval, 1998, pp. 46\u201354","DOI":"10.1145\/290941.290956"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB25","unstructured":"http:\/\/www.excite.com, Excite Directory"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB26","unstructured":"http:\/\/dmoz.org, Open Directory Project (ODP)"},{"key":"10.1016\/S0020-0255(03)00169-5_BIB27","unstructured":"http:\/\/www.yahoo.com, Yahoo! Web Search Directory"}],"container-title":["Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025503001695?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0020025503001695?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,3,17]],"date-time":"2019-03-17T06:56:19Z","timestamp":1552805779000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0020025503001695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,10]]},"references-count":27,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2003,10]]}},"alternative-id":["S0020025503001695"],"URL":"https:\/\/doi.org\/10.1016\/s0020-0255(03)00169-5","relation":{},"ISSN":["0020-0255"],"issn-type":[{"value":"0020-0255","type":"print"}],"subject":[],"published":{"date-parts":[[2003,10]]}}}