{"id":"https://openalex.org/W2145727241","doi":"https://doi.org/10.1145/1458082.1458241","title":"Scalable community discovery on textual data with relations","display_name":"Scalable community discovery on textual data with relations","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2145727241","doi":"https://doi.org/10.1145/1458082.1458241","mag":"2145727241"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5078578035","display_name":"Huajing Li","orcid":"https://orcid.org/0000-0003-4207-8351"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huajing Li","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047496977","display_name":"Zaiqing Nie","orcid":"https://orcid.org/0000-0002-1134-2343"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zaiqing Nie","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091716232","display_name":"Wang-Chien Lee","orcid":"https://orcid.org/0000-0002-8949-489X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang-Chien Lee","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025631695","display_name":"Ji-Rong Wen","orcid":"https://orcid.org/0000-0002-9777-9676"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ji-Rong Wen","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5078578035"],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":4.7336,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.95216661,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1203","last_page":"1212"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9991000294685364,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982401847839355},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7904115319252014},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.6933578252792358},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6482921838760376},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5463781952857971},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5241097211837769},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5008647441864014},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.4631793797016144},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.43132826685905457},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4286007583141327},{"id":"https://openalex.org/keywords/relation","display_name":"Relation (database)","score":0.427725613117218},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41784459352493286},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4012437164783478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982401847839355},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7904115319252014},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.6933578252792358},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6482921838760376},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5463781952857971},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5241097211837769},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5008647441864014},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.4631793797016144},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.43132826685905457},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4286007583141327},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.427725613117218},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41784459352493286},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4012437164783478},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1458082.1458241","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458241","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.219.4492","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.219.4492","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.microsoft.com/users/znie/cikm2008_community.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5299999713897705}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1589763115","https://openalex.org/W1612003148","https://openalex.org/W1738091461","https://openalex.org/W1880262756","https://openalex.org/W1963523624","https://openalex.org/W1971272745","https://openalex.org/W1984374364","https://openalex.org/W2001082470","https://openalex.org/W2020423193","https://openalex.org/W2030035054","https://openalex.org/W2049701036","https://openalex.org/W2069078812","https://openalex.org/W2108346334","https://openalex.org/W2110909520","https://openalex.org/W2117848638","https://openalex.org/W2118668678","https://openalex.org/W2127137551","https://openalex.org/W2138228978","https://openalex.org/W2147152072","https://openalex.org/W2150384816","https://openalex.org/W2166001595","https://openalex.org/W2166559705","https://openalex.org/W2169206507","https://openalex.org/W6667487258"],"related_works":["https://openalex.org/W4296209631","https://openalex.org/W4234886518","https://openalex.org/W2389591058","https://openalex.org/W2382112581","https://openalex.org/W3124036233","https://openalex.org/W4229787472","https://openalex.org/W3097449145","https://openalex.org/W2486541857","https://openalex.org/W2108840191","https://openalex.org/W3200375535"],"abstract_inverted_index":{"Every":[0],"piece":[1],"of":[2,35,81,107,164,173],"textual":[3,85],"data":[4,60],"is":[5,34,127,182],"generated":[6],"as":[7,40,42,87,89,162],"a":[8,94,105,123,145],"method":[9,202],"to":[10,37,45,69,113,143,157,189,206],"convey":[11],"its":[12],"authors'":[13],"opinion":[14],"regarding":[15],"specific":[16],"topics.":[17],"Authors":[18],"deliberately":[19],"organize":[20],"their":[21,43],"writings":[22],"and":[23,50,62,116,209],"create":[24],"links,":[25],"i.e.,":[26],"references,":[27],"acknowledgments,":[28],"for":[29,76,97,150],"better":[30],"expression.":[31],"Thereafter,":[32],"it":[33],"interest":[36],"study":[38],"texts":[39],"well":[41,88],"relations":[44],"understand":[46],"the":[47,57,120,130,171,186,200],"underlying":[48],"topics":[49],"communities.":[51],"Although":[52],"many":[53],"efforts":[54,142],"exist":[55],"in":[56,59,129],"literature":[58],"clustering":[61,222],"topic":[63],"mining,":[64],"they":[65],"are":[66,111],"not":[67],"applicable":[68],"community":[70,125,134,147],"discovery":[71,148],"on":[72,104],"large":[73],"document":[74,152],"corpus":[75,207],"several":[77],"reasons.":[78],"First,":[79],"few":[80],"them":[82],"consider":[83],"both":[84],"attributes":[86],"relations.":[90],"Second,":[91],"scalability":[92,205],"remains":[93],"significant":[95],"issue":[96],"large-scale":[98,151],"datasets.":[99],"Additionally,":[100],"most":[101],"algorithms":[102],"rely":[103],"set":[106],"initial":[108,174,194],"parameters":[109],"that":[110,185,199],"hard":[112],"be":[114],"captured":[115],"tuned.":[117],"Motivated":[118],"by":[119],"aforementioned":[121],"observations,":[122],"hierarchical":[124],"model":[126],"proposed":[128,201],"paper":[131],"which":[132],"distinguishes":[133],"cores":[135,161],"from":[136],"affiliated":[137],"members.":[138],"We":[139],"present":[140],"our":[141],"develop":[144],"scalable":[146],"solution":[149],"corpus.":[153],"Our":[154],"proposal":[155],"tries":[156],"quickly":[158],"identify":[159],"potential":[160],"seeds":[163],"communities":[165,192],"through":[166],"relation":[167],"analysis.":[168],"To":[169],"eliminate":[170],"influence":[172],"parameters,":[175],"an":[176],"innovative":[177],"attribute-based":[178],"core":[179],"merge":[180],"process":[181],"introduced":[183],"so":[184],"algorithm":[187],"promises":[188],"return":[190],"consistent":[191],"regardless":[193],"parameters.":[195],"Experimental":[196],"results":[197],"suggest":[198],"has":[203],"high":[204],"size":[208],"feature":[210],"dimensionality,":[211],"with":[212,220],"more":[213],"than":[214],"15":[215],"topical":[216],"precision":[217],"improvement":[218],"compared":[219],"popular":[221],"techniques.":[223]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":8}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}