{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T16:21:00Z","timestamp":1759940460626,"version":"3.40.5"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[1999,12,1]],"date-time":"1999-12-01T00:00:00Z","timestamp":944006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1999,12,1]],"date-time":"1999-12-01T00:00:00Z","timestamp":944006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Artificial Intelligence Review"],"published-print":{"date-parts":[[1999,12]]},"DOI":"10.1023\/a:1006596506229","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T02:18:38Z","timestamp":1040523518000},"page":"409-435","source":"Crossref","is-referenced-by-count":10,"title":["Topic Distillation and Spectral Filtering"],"prefix":"10.1007","volume":"13","author":[{"given":"Soumen","family":"Chakrabarti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byron E.","family":"Dom","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Gibson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ravi","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Prabhakar","family":"Raghavan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sridhar","family":"Rajagopalan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Tomkins","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"187365_CR1","doi-asserted-by":"crossref","unstructured":"Arocena, G. O., Mendelzon, A. O. & Mihaila, G. A. (1997). Applications of a Web Query Language. Proc. 6th International World Wide Web Conference.","DOI":"10.1016\/S0169-7552(97)00043-3"},{"key":"187365_CR2","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<444::AID-ASI12>3.0.CO;2-J","volume":"41","author":"A. E. Bayer","year":"1990","unstructured":"Bayer, A. E., Smart, J. C. & McLaughlin, G. W. (1990). Mapping Intellectual Structure of Scientific Subfields Through Author Co-Citations. J. American Soc. Info. Sci.\n41: 444-452.","journal-title":"J. American Soc. Info. Sci."},{"key":"187365_CR3","doi-asserted-by":"crossref","unstructured":"Bharat, K. & Broder, Andrei. (1998). A Technique for Measuring the Relative Size and Overlap of Public Web Search Engines. Proceedings of the 7th World-Wide Web Conference (WWW7).","DOI":"10.1016\/S0169-7552(98)00127-5"},{"key":"187365_CR4","doi-asserted-by":"crossref","unstructured":"Bharat K. & Henzinger, M. R. (1998). Improved Algorithms for Topic Distillation in a Hyperlinked Environment. Proceedings of the 21st International ACM SIGIR Conference on Research and Development in Information Retrieval, 469-477. Compressed postscript version: http:\/\/www.research.digital.com\/SRC\/personal\/monika\/papers\/sigir98.ps.gz.","DOI":"10.1145\/290941.290972"},{"key":"187365_CR5","unstructured":"Bollob\u00e1s B. (1985). Random Graphs. Academic Press."},{"key":"187365_CR6","doi-asserted-by":"crossref","unstructured":"Botafogo, Rodrigo A. & Shneiderman, Ben (1991). Identifying Aggregates in Hypertext Structures. Proceedings of ACM Hypertext '91: 63-74.","DOI":"10.1145\/122974.122981"},{"key":"187365_CR7","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1145\/146802.146826","volume":"10","author":"R. Botafogo","year":"1992","unstructured":"Botafogo, R., Rivlin, E. & Shneiderman, B. (1992). Structural Analysis of Hypertext: Identifying Hierarchies and Useful Metrics. ACM Trans. Inf. Sys.\n10: 142-180.","journal-title":"ACM Trans. Inf. Sys."},{"key":"187365_CR8","doi-asserted-by":"crossref","unstructured":"Brin, S. & Page, L. (1998). The Anatomy of a Large-Scale Hypertextual Web Search Engine. Proceedings of the 7th World-Wide Web Conference (WWW7).","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"187365_CR9","doi-asserted-by":"crossref","unstructured":"Bruce Croft, W. & Turtle, Howard (1989). A Retrieval Model for Incorporazting Hypertext Links. Proceedings of ACM Hypertext '89, 213-224.","DOI":"10.1145\/74224.74242"},{"key":"187365_CR10","doi-asserted-by":"crossref","unstructured":"Carri\u00e8re, J. & Kazman, R. (1997). WebQuery: Searching and Visualizing the Web Through Connectivity. Proc 6th International World Wide Web Conference.","DOI":"10.1016\/S0169-7552(97)00062-7"},{"key":"187365_CR11","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Dom, B., Gibson, D., Kleinberg, J., Raghvan, P. & Rajagopalan, S. (1998). Automatic Resource Compilation by Analyzing Hyperlink Structure and Associated Text. Proceedings of the 7th World-Wide Web Conference (WWW7).","DOI":"10.1016\/S0169-7552(98)00087-7"},{"key":"187365_CR12","unstructured":"Chakrabarti, S., Dom, B. E., Gibson, D., Kumar, R., Raghavan, P., Rajagopalan, S. & Tomkins, A. (1998). Spectral Filtering for Resource Discovery. SIGIR 98 Workshop on Hypertext Information Retrieval and the Web."},{"key":"187365_CR13","unstructured":"Chakrabarti, S., Dom, B., Agrawal, R. & Raghavan, P. (1997). Using Taxonomy, Discriminants, and Signatures to Navigate in Text Databases. 23rd International Conference on Very Large Data Bases (VLDB). Athens, Greece."},{"key":"187365_CR14","doi-asserted-by":"crossref","unstructured":"Chakrabarti, S., Dom, B. & Indyk, P. (1998). Enhanced Hypertext Classification Using Hyperlinks. ACM SIGMOD Conference on Management of Data. Seattle, WA.","DOI":"10.1145\/276304.276332"},{"key":"187365_CR15","doi-asserted-by":"crossref","unstructured":"Chen, C. (1997). Structuring and Visualizing the WWW by Generalized Similarity Analysis. Proc. 8th ACM Conference on Hypertext, 177-186.","DOI":"10.1145\/267437.267456"},{"key":"187365_CR16","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/0306-4573(87)90017-3","volume":"23","author":"P. R. Cohen","year":"1987","unstructured":"Cohen, P. R. & Kjeldsen, R. (1987). Information Retrieval by Constrained Spreading Activation in Semantic Networks. Information Processing and Management\n23: 255-268.","journal-title":"Information Processing and Management"},{"key":"187365_CR17","doi-asserted-by":"crossref","unstructured":"Cutting, D. R., Pedersen, J. O., Karger, D. R. & Turkey, J. W. (1992). Scatter\/Gather: A Cluster-Based Approach to Browsing Large Document Collections. Proceedings of ACM SIGIR, 318-329.","DOI":"10.1145\/133160.133214"},{"key":"187365_CR18","doi-asserted-by":"crossref","unstructured":"Deerwester, S., Dumais, S., Landauer, T., Furnas, G. & Harshman, R. (1990). Indexing by Latent Semantic Analysis. J. American Soc. Info. Sci.\n41.","DOI":"10.1002\/(SICI)1097-4571(199009)41:6<391::AID-ASI1>3.0.CO;2-9"},{"key":"187365_CR19","unstructured":"Digital Equipment Corporation. Alta Vista Search Engine, altavista, digital.com\/."},{"key":"187365_CR20","unstructured":"Donath, W. E. & Hoffman, A. J. (1972). Algorithms for Partitioning of Graphs and Computer Logic Based on Eigenvectors of Connections Matrices. IBM Technical Disclosure Bulletin\n15."},{"key":"187365_CR21","unstructured":"Excite Inc. Excite, www.excite.com."},{"key":"187365_CR22","unstructured":"FindLaw. FindLaw \u2014 LawCrawler, www.lawcrawler, com."},{"key":"187365_CR23","unstructured":"Frakes, W. & Baeza-Yates, R. (eds.) (1992). Information Retrieval: Data Structures and Algorithms. Prentice-Hall."},{"issue":"7","key":"187365_CR24","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1145\/48511.48518","volume":"31","author":"M. E. Frisse","year":"19??","unstructured":"Frisse, M. E. (19??). Searching for Information in a Hypertext Medical Handbook. Communications of the ACM\n31(7): 880-886.","journal-title":"Communications of the ACM"},{"key":"187365_CR25","volume-title":"An Introduction to Statistical Pattern Recognition","author":"K. Fukunaga","year":"1990","unstructured":"Fukunaga, K. (1990). An Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press: New York.","edition":"2nd edn."},{"key":"187365_CR26","doi-asserted-by":"crossref","unstructured":"Furuta, R., Shipman III, F. M., Marshall, C. C., Brenner, C. & Hsieh, H-W. (1997). Hypertext Paths and the World-Wide Web: experiences with Walden's Paths. Proc. 8th ACM Conference on Hypertext, 167-176.","DOI":"10.1145\/267437.267455"},{"key":"187365_CR27","doi-asserted-by":"crossref","first-page":"471","DOI":"10.1126\/science.178.4060.471","volume":"178","author":"E. Garfield","year":"1972","unstructured":"Garfield, E. (1972). Citation Analysis as a Tool in Journal Evaluation. Science\n178: 471-479.","journal-title":"Science"},{"key":"187365_CR28","unstructured":"Garfield, E. (1994). The Impact Factor. Current Contents, June 20."},{"key":"187365_CR29","doi-asserted-by":"crossref","unstructured":"Golovchinsky, G. (1997). What the Query Told the Link: The Integration of Hypertext and Information Retrieval. Proc. 8th ACM Conference on Hypertext, 67-74.","DOI":"10.1145\/267437.267445"},{"key":"187365_CR30","unstructured":"Golub, G. & Van Loan, C. F. (1989). Matrix Computations. John Hopkins University Press."},{"key":"187365_CR31","unstructured":"Infoseek Corporation. Infoseek search engine, www.infoseek.com."},{"key":"187365_CR32","unstructured":"International Business Machines. IBM patent server, patent.womplex.ibm.com."},{"key":"187365_CR33","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1002\/asi.5090140103","volume":"14","author":"M. M. Kessler","year":"1963","unstructured":"Kessler, M. M. (1963). Bibliographic Coupling Between Scientific Papers. American Documentation\n14: 10-25.","journal-title":"American Documentation"},{"key":"187365_CR34","unstructured":"Kleinberg, J. (1997). Authoritative Sources in a Hyperlinked Environment. Proc. ACM-SIAM Symposium on Discrete Algorithms, 1998. Also appears as IBM Research Report RJ 10076(91892) May and as www.cs.cornell.edu\/home\/kleinber\/auth.ps."},{"key":"187365_CR35","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1002\/asi.4630340507","volume":"34","author":"T. R. Kochtanek","year":"1983","unstructured":"Kochtanek, T. R. (1983). Document Clustering Using Macro Retrieval Techniques\u201d, J. American Soc. Info. Sci.\n34: 356-359.","journal-title":"J. American Soc. Info. Sci."},{"key":"187365_CR36","unstructured":"Larson, R. (1996). \u201cBibliometrics of the World Wide Web: An Exploratory Analysis of the Intellectual Structure of Cyberspace\u201d. Ann. Meeting of the American Soc. Info. Sci."},{"issue":"4","key":"187365_CR37","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1108\/eb026920","volume":"49","author":"M. Liu","year":"1993","unstructured":"Liu, Mengxiong. (1993). Progress in Documentation the Complexities of Citation Practice: A Review of Citation Studies. J. Documentation\n49(4): 370-408.","journal-title":"J. Documentation"},{"key":"187365_CR38","unstructured":"Marchiori, Massimo (1997). The Quest for Correct Information on the Web: Hyper Search Engines. The 6th International World Wide Web Conference (WWW6). Also available at http:\/\/atlanta.cs.nchu.edu.tw\/www\/PAPER222.html."},{"key":"187365_CR39","doi-asserted-by":"crossref","unstructured":"Mukherjea, S. & Hara, Y. (1997). Focus+Context Views of World-Wide Web Nodes. Proc. 8th ACM Conference on Hypertext, 187-196.","DOI":"10.1145\/267437.267457"},{"key":"187365_CR40","unstructured":"Page, Larry. (1997). PageRank: Bringing Order to the Web. Stanford Digital Libraries Working Paper 1997-0072. http:\/\/www-pcd.stanford.edu\/page\/papers\/pagerank\/index.htm."},{"key":"187365_CR41","doi-asserted-by":"crossref","unstructured":"Pirolli, P., Pitkow, J. & Rao, R. (1996). Silk from a Sow's Ear: Extracting Usable Structures from the Web. Proc. ACM SIGCHI Conference on Human Factors in Computing (http:\/\/www.acm.org:82\/sigs\/sigchi\/chi96\/proceedings\/papers\/Pirolli_2\/ppw.html).","DOI":"10.1145\/238386.238450"},{"key":"187365_CR42","unstructured":"van Rijsbergen, C. J. (1979). Information Retrieval. Butterworths. Also at dcs.glasgow.ac.uk.\/Keith\/Preface.html."},{"issue":"2","key":"187365_CR43","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1145\/175235.175242","volume":"37","author":"E. Rivlin","year":"1994","unstructured":"Rivlin, E., Botaforgo, R. & Shneiderman, B. (1994). Navigating in Hyperspace: Designing a Structure-Based Toolbox. Communications of the ACM\n37(2): 87-96.","journal-title":"Communications of the ACM"},{"key":"187365_CR44","doi-asserted-by":"crossref","first-page":"775","DOI":"10.1002\/(SICI)1097-4571(199610)47:10<775::AID-ASI5>3.0.CO;2-#","volume":"47","author":"R. Rousseau","year":"1996","unstructured":"Rousseau, R. & Van Hooydonk, G. (1996). Journal Production and Journal Impact Factors, J. American Soc. Info. Sci.\n47: 775-780.","journal-title":"J. American Soc. Info. Sci."},{"key":"187365_CR45","volume-title":"Automatic Text Processing","author":"G. Salton","year":"1989","unstructured":"Salton, G. (1989). Automatic Text Processing. Addison-Wesley: Reading, MA."},{"key":"187365_CR46","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1006\/imms.1993.1047","volume":"38","author":"J. Savoy","year":"1993","unstructured":"Savoy, Jaques (1993). Searching Information in Hypertext Systems Using Multiple Sources of Evidence. Int. J. Man-Machine Studies\n38: 1017-1030.","journal-title":"Int. J. Man-Machine Studies"},{"issue":"2","key":"187365_CR47","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/S0306-4573(96)85003-5","volume":"32","author":"J. Savoy","year":"1996","unstructured":"Savoy, Jaques (1996). An Extended Vector-Processing Scheme for Searching Information in Hypertext Systems. Information Processing and Management\n32(2): 155-170.","journal-title":"Information Processing and Management"},{"issue":"3","key":"187365_CR48","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1002\/(SICI)1097-4571(199703)48:3<235::AID-ASI5>3.0.CO;2-Y","volume":"48","author":"J. Savoy","year":"1997","unstructured":"Savoy, Jaques (1997). Ranking Schemes in Hybrid Boolean Systems: A New Approach. J. Am. Soc. Information Sci.\n48(3): 235-253.","journal-title":"J. Am. Soc. Information Sci."},{"key":"187365_CR49","doi-asserted-by":"crossref","unstructured":"Schwanke, R. W. & Platoff, M. A. (1993). Cross References Are Features. In Hanson, S. J., Remmele, W. & Rivest, R. L. (eds.) Machine Learning: From Theory to Applications. Springer.","DOI":"10.1007\/3-540-56483-7_26"},{"key":"187365_CR50","doi-asserted-by":"crossref","first-page":"669","DOI":"10.1002\/(SICI)1097-4571(199110)42:9<669::AID-ASI5>3.0.CO;2-Y","volume":"42","author":"W. M. Shaw","year":"1991","unstructured":"Shaw, W. M. (1991). Subject and Citation Indexing. Part I: The Clustering Structure of Composite Representations in the Cystic Fibrosis Document Collection. J. American Soc. Info. Sci.\n42: 669-675.","journal-title":"J. American Soc. Info. Sci."},{"key":"187365_CR51","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1002\/(SICI)1097-4571(199110)42:9<676::AID-ASI6>3.0.CO;2-2","volume":"42","author":"W. M. Shaw","year":"1991","unstructured":"Shaw, W. M. (1991). Subject and Citation Indexing. Part II: The Optimal, Cluster-Based Retrieval Performance of Composite Representations. J. American Soc. Info. Sci.\n42: 676-684.","journal-title":"J. American Soc. Info. Sci."},{"key":"187365_CR52","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1002\/asi.4630240406","volume":"24","author":"H. Small","year":"1973","unstructured":"Small, H. (1973). Co-Citation in the Scientific Literature: A New Measure of the Relationship Between Two Documents. J. American Soc. Info. Sci.\n24: 265-269.","journal-title":"J. American Soc. Info. Sci."},{"key":"187365_CR53","doi-asserted-by":"crossref","unstructured":"Spertus, E. (1997). ParaSite: Mining Structural Information on the Web. Proc. 6th International World Wide Web Conference.","DOI":"10.1016\/S0169-7552(97)00033-0"},{"key":"187365_CR54","doi-asserted-by":"crossref","unstructured":"Spielman, D. & Teng, S. (1996). Spectral Partitioning Works: Planar Graphs and Finite-Element Meshes. Processedings of the 37th IEEE Symposium on Foundations of Computer Science.","DOI":"10.1109\/SFCS.1996.548468"},{"key":"187365_CR55","unstructured":"TREC \u2014 Text REtrieval Conference. Co-sponsored by the National Institute of Standards & Technology (NIST) and the Information Technology Office of the Defense Advanced Research Projects Agency (DARPA) as part of the TIPSTER Text Program. (http:\/\/trec.nist.gov\/)."},{"key":"187365_CR56","doi-asserted-by":"crossref","unstructured":"Wang, Q., Baldonado, M. & Winograd, T. (1997). SenseMaker: An Information-Exploration Interface Supporting the Contextual Evaluation of a User's Interests. Proc. ACM SIGCHI Conference on Human Factors in Computing.","DOI":"10.1145\/258549.258563"},{"key":"187365_CR57","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/0020-0271(74)90058-8","volume":"10","author":"B. H. Weinberg","year":"1974","unstructured":"Weinberg, Bella Hass (1974). Bibliographic Coupling: A Review. Information Storage and Retrieval\n10: 189-196.","journal-title":"Information Storage and Retrieval"},{"key":"187365_CR58","unstructured":"Weinreb, Lloyd L. (1982). Leading Constitutional Cases on Criminal Justice. Foundation Press."},{"key":"187365_CR59","doi-asserted-by":"crossref","unstructured":"Weiss, R., Velez, B., Sheldon, M., Nemprempre, C., Szilagyi, P. & Gifford, D. K. (1996). HyPursuit: A Hierarchical Network Search Engine that Exploits Content-Link Hypertext Clustering. Proceedings of the Seventh ACM Conference on Hypertext.","DOI":"10.1145\/234828.234846"},{"key":"187365_CR60","unstructured":"White, H. D. & McCain, K. W. (1989). Bibliometrics. Ann. Rev. Info. Sci. and Technology, 119-186. Elsevier."},{"issue":"5","key":"187365_CR61","doi-asserted-by":"crossref","first-page":"577","DOI":"10.1016\/0306-4573(88)90027-1","volume":"24","author":"P. Willet","year":"1988","unstructured":"Willet, Peter. (1988). Recent Trends in Hierarchical Document Clustering: a Critical Review. Information Processing and Management\n24(5): 577-597.","journal-title":"Information Processing and Management"},{"key":"187365_CR62","unstructured":"World Wide Web Consortium. World Wide Web Virtual Library, www.w3.org\/vl\/."},{"key":"187365_CR63","unstructured":"Yahoo! Corp. Yahoo!, www.yahoo.com."}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1006596506229.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1006596506229\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1006596506229.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,18]],"date-time":"2025-05-18T04:30:01Z","timestamp":1747542601000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1006596506229"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,12]]},"references-count":63,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[1999,12]]}},"alternative-id":["187365"],"URL":"https:\/\/doi.org\/10.1023\/a:1006596506229","relation":{},"ISSN":["0269-2821","1573-7462"],"issn-type":[{"type":"print","value":"0269-2821"},{"type":"electronic","value":"1573-7462"}],"subject":[],"published":{"date-parts":[[1999,12]]}}}