{"id":"https://openalex.org/W2137820941","doi":"https://doi.org/10.1145/1148170.1148241","title":"Document clustering with prior knowledge","display_name":"Document clustering with prior knowledge","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2137820941","doi":"https://doi.org/10.1145/1148170.1148241","mag":"2137820941"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033646805","display_name":"Xiang Ji","orcid":"https://orcid.org/0000-0002-0240-8582"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiang Ji","raw_affiliation_strings":["Yahoo! Inc., Sunnyvale, CA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Inc., Sunnyvale, CA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070905937","display_name":"Wei Xu","orcid":"https://orcid.org/0000-0002-7044-3232"},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Xu","raw_affiliation_strings":["NEC Labs America, Inc., Cupertino, CA"],"affiliations":[{"raw_affiliation_string":"NEC Labs America, Inc., Cupertino, CA","institution_ids":["https://openalex.org/I4210107353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033646805"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":13.1007,"has_fulltext":false,"cited_by_count":128,"citation_normalized_percentile":{"value":0.98793223,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7919455766677856},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7062461972236633},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6510739326477051},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.544803261756897},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4786185622215271},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46588200330734253},{"id":"https://openalex.org/keywords/vertex","display_name":"Vertex (graph theory)","score":0.4615483582019806},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4208308458328247},{"id":"https://openalex.org/keywords/single-linkage-clustering","display_name":"Single-linkage clustering","score":0.41928520798683167},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4156866669654846},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38745877146720886},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.38048872351646423},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.16809022426605225},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.1430395245552063},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10838043689727783}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7919455766677856},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7062461972236633},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6510739326477051},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.544803261756897},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4786185622215271},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46588200330734253},{"id":"https://openalex.org/C80899671","wikidata":"https://www.wikidata.org/wiki/Q1304193","display_name":"Vertex (graph theory)","level":3,"score":0.4615483582019806},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4208308458328247},{"id":"https://openalex.org/C22648726","wikidata":"https://www.wikidata.org/wiki/Q7523744","display_name":"Single-linkage clustering","level":5,"score":0.41928520798683167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4156866669654846},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38745877146720886},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.38048872351646423},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.16809022426605225},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.1430395245552063},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10838043689727783},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1148170.1148241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6000000238418579}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W37713582","https://openalex.org/W104722501","https://openalex.org/W146900863","https://openalex.org/W1527883571","https://openalex.org/W1558467664","https://openalex.org/W1604224286","https://openalex.org/W1938542669","https://openalex.org/W1977556410","https://openalex.org/W1981276685","https://openalex.org/W1992419399","https://openalex.org/W1996764654","https://openalex.org/W2005422315","https://openalex.org/W2037603696","https://openalex.org/W2102524069","https://openalex.org/W2107008379","https://openalex.org/W2107968230","https://openalex.org/W2110441437","https://openalex.org/W2111557120","https://openalex.org/W2115657355","https://openalex.org/W2121947440","https://openalex.org/W2134089414","https://openalex.org/W2134737843","https://openalex.org/W2137137397","https://openalex.org/W2139823104","https://openalex.org/W2139850885","https://openalex.org/W2155754954","https://openalex.org/W2163399552","https://openalex.org/W2560674852","https://openalex.org/W2798909945","https://openalex.org/W4241122026","https://openalex.org/W4252684946"],"related_works":["https://openalex.org/W4241767317","https://openalex.org/W2188840951","https://openalex.org/W2101637161","https://openalex.org/W2056194206","https://openalex.org/W2171610853","https://openalex.org/W3092684173","https://openalex.org/W2160785859","https://openalex.org/W2551482053","https://openalex.org/W1999117613","https://openalex.org/W4280580511"],"abstract_inverted_index":{"Document":[0],"clustering":[1,35,103,141],"is":[2,10,51,64,94,105,154],"an":[3],"important":[4],"tool":[5],"for":[6,25],"text":[7],"analysis":[8,28],"and":[9,29,56,131,152],"used":[11],"in":[12,47],"many":[13],"different":[14],"applications.":[15],"We":[16,118],"propose":[17],"to":[18,84,86,122,127],"incorporate":[19],"prior":[20,76,92],"knowledge":[21,77,93],"of":[22,42,62,70,80,99,112],"cluster":[23,27],"membership":[24],"document":[26,34,50,102,140],"develop":[30],"a":[31,40,54,60,97,155],"novel":[32],"semi-supervised":[33,158],"model.":[36],"The":[37,75,101],"method":[38,126],"models":[39],"set":[41,98],"documents":[43,81],"with":[44,66,147],"weighted":[45,65],"graph":[46,114],"which":[48],"each":[49,57],"represented":[52],"as":[53],"vertex,":[55],"edge":[58],"connecting":[59],"pair":[61],"vertices":[63],"the":[67,71,87,91,109,113,116,120,123,129,138],"similarity":[68],"value":[69],"two":[72],"corresponding":[73],"documents.":[74],"indicates":[78],"pairs":[79],"that":[82,137],"known":[83],"belong":[85],"same":[88],"cluster.":[89],"Then,":[90],"transformed":[95],"into":[96],"constraints.":[100,117],"task":[104],"accomplished":[106],"by":[107],"finding":[108],"best":[110],"cuts":[111],"under":[115],"apply":[119],"model":[121,142],"Normalized":[124],"Cut":[125],"demonstrate":[128],"idea":[130],"concept.":[132],"Our":[133],"experimental":[134],"evaluations":[135],"show":[136],"proposed":[139],"reveals":[143],"remarkable":[144],"performance":[145],"improvements":[146],"very":[148,156],"limited":[149],"training":[150],"samples,":[151],"hence":[153],"effective":[157],"classification":[159],"tool.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":9},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":19}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}