{"id":"https://openalex.org/W2058846446","doi":"https://doi.org/10.1145/2396761.2398615","title":"Clustering short text using Ncut-weighted non-negative matrix factorization","display_name":"Clustering short text using Ncut-weighted non-negative matrix factorization","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2058846446","doi":"https://doi.org/10.1145/2396761.2398615","mag":"2058846446"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101427643","display_name":"Xiaohui Yan","orcid":"https://orcid.org/0000-0003-0795-9321"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaohui Yan","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088621320","display_name":"Jiafeng Guo","orcid":"https://orcid.org/0000-0002-9509-8674"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiafeng Guo","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100677836","display_name":"Shenghua Liu","orcid":"https://orcid.org/0000-0003-2120-3598"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenghua Liu","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029998682","display_name":"Xueqi Cheng","orcid":"https://orcid.org/0000-0002-5201-8195"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xue-qi Cheng","raw_affiliation_strings":["Institute of Computing Technology, CAS, Beijing, China","Institute of Computing Technology, CAS, Beijing, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"Institute of Computing Technology, CAS, Beijing, China#TAB#","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100645705","display_name":"Yanfeng Wang","orcid":"https://orcid.org/0000-0002-3196-2347"},"institutions":[{"id":"https://openalex.org/I4210134178","display_name":"Sohu (China)","ror":"https://ror.org/02sfdh709","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210134178"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanfeng Wang","raw_affiliation_strings":["Sogou Inc., Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sogou Inc., Beijing, China","institution_ids":["https://openalex.org/I4210134178"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2259","last_page":"2262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9962999820709229,"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":0.9962999820709229,"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/T10057","display_name":"Face and Expression Recognition","score":0.992900013923645,"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"}},{"id":"https://openalex.org/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/weighting","display_name":"Weighting","score":0.8804210424423218},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.8209935426712036},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7393984794616699},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7169882655143738},{"id":"https://openalex.org/keywords/tf\u2013idf","display_name":"tf\u2013idf","score":0.7057343125343323},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6464414596557617},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5855136513710022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5759798288345337},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.5668089985847473},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5659618377685547},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.48984667658805847},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3615950345993042}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.8804210424423218},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.8209935426712036},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7393984794616699},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7169882655143738},{"id":"https://openalex.org/C81758059","wikidata":"https://www.wikidata.org/wiki/Q796584","display_name":"tf\u2013idf","level":3,"score":0.7057343125343323},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6464414596557617},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5855136513710022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5759798288345337},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.5668089985847473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5659618377685547},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.48984667658805847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3615950345993042},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2396761.2398615","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398615","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7200000286102295}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W1532325895","https://openalex.org/W1914599625","https://openalex.org/W1974490937","https://openalex.org/W2013029404","https://openalex.org/W2121947440","https://openalex.org/W2135674549"],"related_works":["https://openalex.org/W2127243424","https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W2075222291"],"abstract_inverted_index":{"Non-negative":[0],"matrix":[1],"factorization":[2],"(NMF)":[3],"has":[4],"been":[5],"successfully":[6],"applied":[7],"in":[8,53],"document":[9,94],"clustering.":[10,121],"However,":[11],"experiments":[12],"on":[13,82,93,102,106,118],"short":[14,54,119],"texts,":[15,55],"such":[16],"as":[17],"microblogs,":[18],"Q&A":[19],"documents":[20],"and":[21,42,51],"news":[22],"titles,":[23],"suggest":[24],"unsatisfactory":[25],"performance":[26,117],"of":[27,60],"NMF.":[28],"An":[29],"major":[30],"reason":[31],"is":[32],"that":[33],"the":[34,47,58,77,83,96],"traditional":[35],"term":[36,70,84,103],"weighting":[37,71,98,112],"schemes,":[38],"like":[39],"binary":[40],"weight":[41],"tfidf,":[43],"cannot":[44],"well":[45],"capture":[46],"terms'":[48,100],"discriminative":[49],"power":[50],"importance":[52],"due":[56],"to":[57],"sparsity":[59],"data.":[61],"To":[62],"tackle":[63],"this":[64],"problem,":[65],"we":[66],"proposed":[67],"a":[68],"novel":[69],"scheme":[72,113],"for":[73],"NMF,":[74],"derived":[75],"from":[76,88],"Normalized":[78],"Cut":[79],"(Ncut)":[80],"problem":[81],"affinity":[85],"graph.":[86],"Different":[87],"idf,":[89],"which":[90],"emphasizes":[91],"discriminability":[92,101],"level,":[95],"Ncut":[97],"measures":[99],"level.":[104],"Experiments":[105],"two":[107],"data":[108],"sets":[109],"show":[110],"our":[111],"significantly":[114],"boosts":[115],"NMF's":[116],"text":[120]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}