{"id":"https://openalex.org/W2025276985","doi":"https://doi.org/10.1145/2124295.2124363","title":"On clustering heterogeneous social media objects with outlier links","display_name":"On clustering heterogeneous social media objects with outlier links","publication_year":2012,"publication_date":"2012-02-08","ids":{"openalex":"https://openalex.org/W2025276985","doi":"https://doi.org/10.1145/2124295.2124363","mag":"2025276985"},"language":"en","primary_location":{"id":"doi:10.1145/2124295.2124363","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","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/A5100766907","display_name":"Guo-Jun Qi","orcid":"https://orcid.org/0000-0003-3508-1851"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guo-Jun Qi","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028089542","display_name":"Char\u0173 C. Aggarwal","orcid":"https://orcid.org/0000-0003-2579-7581"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charu C. Aggarwal","raw_affiliation_strings":["IBM T.J. Watson Research Center, Hawthorne, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM T.J. Watson Research Center, Hawthorne, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457342","display_name":"Thomas S. Huang","orcid":"https://orcid.org/0000-0001-8474-5859"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Thomas S. Huang","raw_affiliation_strings":["University of Illinois at Urbana-Champaign, Urbana, IL, USA","University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign, Urbana, IL, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana/Champaign, Urbana, IL, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100766907"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.1366,"has_fulltext":false,"cited_by_count":72,"citation_normalized_percentile":{"value":0.91980463,"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":"553","last_page":"562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9984999895095825,"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":0.9947999715805054,"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/cluster-analysis","display_name":"Cluster analysis","score":0.8512733578681946},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7583203315734863},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6006651520729065},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5581833124160767},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.5377293825149536},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4825131595134735},{"id":"https://openalex.org/keywords/social-network","display_name":"Social network (sociolinguistics)","score":0.4656691551208496},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4549403488636017},{"id":"https://openalex.org/keywords/fuzzy-clustering","display_name":"Fuzzy clustering","score":0.4548488259315491},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.4539286494255066},{"id":"https://openalex.org/keywords/constrained-clustering","display_name":"Constrained clustering","score":0.4536523222923279},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4497326910495758},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.44493311643600464},{"id":"https://openalex.org/keywords/link-analysis","display_name":"Link analysis","score":0.43281519412994385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36933398246765137},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.30729711055755615},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12654554843902588}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8512733578681946},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7583203315734863},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6006651520729065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5581833124160767},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.5377293825149536},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4825131595134735},{"id":"https://openalex.org/C4727928","wikidata":"https://www.wikidata.org/wiki/Q17164759","display_name":"Social network (sociolinguistics)","level":3,"score":0.4656691551208496},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4549403488636017},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.4548488259315491},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.4539286494255066},{"id":"https://openalex.org/C27964816","wikidata":"https://www.wikidata.org/wiki/Q5164359","display_name":"Constrained clustering","level":5,"score":0.4536523222923279},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4497326910495758},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.44493311643600464},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.43281519412994385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36933398246765137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30729711055755615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12654554843902588},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2124295.2124363","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2124295.2124363","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the fifth ACM international conference on Web search and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.298.1146","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.298.1146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://charuaggarwal.net/wsdm064-qi.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1604983895","https://openalex.org/W1880262756","https://openalex.org/W1966957716","https://openalex.org/W1971784203","https://openalex.org/W1975536649","https://openalex.org/W1979584682","https://openalex.org/W1996764654","https://openalex.org/W2047940964","https://openalex.org/W2049633694","https://openalex.org/W2083875149","https://openalex.org/W2105193084","https://openalex.org/W2106545428","https://openalex.org/W2111048828","https://openalex.org/W2121947440","https://openalex.org/W2149857793","https://openalex.org/W2152818382","https://openalex.org/W2156919418","https://openalex.org/W2162491758","https://openalex.org/W2165515835","https://openalex.org/W2170337404","https://openalex.org/W2216446631","https://openalex.org/W2293546752","https://openalex.org/W2293605478","https://openalex.org/W2319660501","https://openalex.org/W4241122026","https://openalex.org/W6639619044","https://openalex.org/W6770641979","https://openalex.org/W7048738093"],"related_works":["https://openalex.org/W3146523624","https://openalex.org/W2622412490","https://openalex.org/W2160785859","https://openalex.org/W2087424554","https://openalex.org/W2186905933","https://openalex.org/W3140018618","https://openalex.org/W2101637161","https://openalex.org/W2607137685","https://openalex.org/W2311450085","https://openalex.org/W2473308841"],"abstract_inverted_index":{"The":[0],"clustering":[1,31,46,60,130],"of":[2,9,33,54,68,89,107,149],"social":[3,90,100,142],"media":[4,91,101,143],"objects":[5],"provides":[6,40],"intrinsic":[7],"understanding":[8],"the":[10,34,45,66,75,85,99,129,147,150],"similarity":[11],"relationships":[12],"between":[13],"documents,":[14],"images,":[15],"and":[16,22,87,115,125,145],"their":[17,126],"contextual":[18],"sources.":[19],"Both":[20],"content":[21,88,114],"link":[23,38,116],"structure":[24,86],"provide":[25],"important":[26],"cues":[27],"for":[28,43],"an":[29],"effective":[30],"algorithm":[32,61,131],"underlying":[35],"objects.":[36],"While":[37],"information":[39],"useful":[41],"hints":[42],"improving":[44],"process,":[47],"it":[48],"also":[49,122],"contains":[50],"a":[51,58,95,105,140],"significant":[52],"amount":[53],"noisy":[55,69,119],"information.":[56],"Therefore,":[57],"robust":[59],"is":[62],"required":[63],"to":[64,73,83],"reduce":[65],"impact":[67,127],"links.":[70],"In":[71],"order":[72],"address":[74],"aforementioned":[76],"problems,":[77],"we":[78],"propose":[79],"heterogeneous":[80],"random":[81],"fields":[82],"model":[84],"networks.":[92],"We":[93,136],"design":[94],"probability":[96],"measure":[97],"on":[98,128,139],"networks":[102],"which":[103],"output":[104],"configuration":[106],"clusters":[108],"that":[109],"are":[110],"consistent":[111],"with":[112],"both":[113],"structure.":[117],"Furthermore,":[118],"links":[120],"can":[121,132],"be":[123,133],"detected,":[124],"significantly":[134],"reduced.":[135],"conduct":[137],"experiments":[138],"real":[141],"network":[144],"show":[146],"advantage":[148],"method":[151],"over":[152],"other":[153],"state-of-the-art":[154],"algorithms.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}