{"id":"https://openalex.org/W2095980495","doi":"https://doi.org/10.1145/2740908.2742474","title":"Short-Text Clustering using Statistical Semantics","display_name":"Short-Text Clustering using Statistical Semantics","publication_year":2015,"publication_date":"2015-05-18","ids":{"openalex":"https://openalex.org/W2095980495","doi":"https://doi.org/10.1145/2740908.2742474","mag":"2095980495"},"language":"en","primary_location":{"id":"doi:10.1145/2740908.2742474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2742474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","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/A5041512669","display_name":"Sepideh Seifzadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sepideh Seifzadeh","raw_affiliation_strings":["University of Waterloo, Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013166935","display_name":"Ahmed Farahat","orcid":"https://orcid.org/0000-0002-9828-8051"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Ahmed K. Farahat","raw_affiliation_strings":["university of Waterloo, waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Waterloo, waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039318050","display_name":"Mohamed S. Kamel","orcid":"https://orcid.org/0000-0001-6173-8082"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mohamed S. Kamel","raw_affiliation_strings":["university of Waterloo, waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Waterloo, waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070046659","display_name":"Fakhri Karray","orcid":null},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Fakhri Karray","raw_affiliation_strings":["university of Waterloo, waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"university of Waterloo, waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I151746483"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"8","issue":null,"first_page":"805","last_page":"810"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991999864578247,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991999864578247,"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":0.9986000061035156,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9968000054359436,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7274347543716431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.65562504529953},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.6191778779029846},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.590738832950592},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5812587738037109},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5416685938835144},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5404393076896667},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5155119895935059},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46944352984428406},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.46319741010665894},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4514264166355133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4328114688396454},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4211214482784271},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4142988920211792},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4092784523963928},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32828986644744873}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7274347543716431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65562504529953},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.6191778779029846},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.590738832950592},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5812587738037109},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5416685938835144},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5404393076896667},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5155119895935059},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46944352984428406},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.46319741010665894},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4514264166355133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4328114688396454},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4211214482784271},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4142988920211792},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4092784523963928},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32828986644744873},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2740908.2742474","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2740908.2742474","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th International Conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W195634160","https://openalex.org/W197049292","https://openalex.org/W1246381107","https://openalex.org/W1479897377","https://openalex.org/W1500117362","https://openalex.org/W1516414061","https://openalex.org/W1558808826","https://openalex.org/W1912120252","https://openalex.org/W1956559956","https://openalex.org/W1974406477","https://openalex.org/W2011242591","https://openalex.org/W2028338510","https://openalex.org/W2048110207","https://openalex.org/W2055400882","https://openalex.org/W2058846446","https://openalex.org/W2118013824","https://openalex.org/W2121947440","https://openalex.org/W2144211451","https://openalex.org/W2147504812","https://openalex.org/W2156963321","https://openalex.org/W2165612380","https://openalex.org/W2404400936","https://openalex.org/W4256306241","https://openalex.org/W6630949348"],"related_works":["https://openalex.org/W4255837520","https://openalex.org/W2387011115","https://openalex.org/W4234808182","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377"],"abstract_inverted_index":{"Short":[0],"documents":[1,33],"are":[2,27,105],"typically":[3],"represented":[4],"by":[5,63,180],"very":[6,28,36,41],"sparse":[7],"vectors,":[8],"in":[9,24,47,97,193],"the":[10,35,55,86,94,131,149,160,165,172,175,188,194,207,210],"space":[11],"of":[12,57,133,151,171,190,209],"terms.":[13,69,143],"In":[14,49,70,144],"this":[15,53,100,117,145],"case,":[16],"traditional":[17],"techniques":[18],"for":[19,123,174],"calculating":[20,139],"text":[21],"similarity":[22,110],"results":[23],"measures":[25],"which":[26],"close":[29],"to":[30,51,163,187,202],"zero,":[31],"since":[32],"even":[34],"similar":[37],"ones":[38],"have":[39,79,203],"a":[40,121,152],"few":[42,153],"or":[43],"mostly":[44],"no":[45],"terms":[46,84,92,158,173,183,201],"common.":[48],"order":[50],"alleviate":[52],"limitation,":[54],"representation":[56],"short-text":[58],"segments":[59,76,104],"should":[60,112],"be":[61,113],"enriched":[62],"incorporating":[64],"information":[65],"about":[66],"correlation":[67,140,167,212],"between":[68,141],"other":[71,98],"words,":[72,82],"if":[73],"two":[74],"short":[75],"do":[77],"not":[78],"any":[80],"common":[81],"but":[83],"from":[85,93],"first":[87],"segment":[88,96],"appear":[89],"frequently":[90],"with":[91,159,184],"second":[95],"documents,":[99],"means":[101],"that":[102],"these":[103,157],"semantically":[106],"related,":[107],"and":[108,155,214],"their":[109,191],"measure":[111],"high.":[114],"Towards":[115],"achieving":[116],"goal,":[118],"we":[119,147],"employ":[120],"method":[122,162,177],"enhancing":[124],"document":[125,195],"clustering":[126],"using":[127,156],"statistical":[128],"semantics.":[129],"However,":[130],"problem":[132],"high":[134],"computation":[135],"time":[136],"arises":[137],"when":[138],"all":[142],"work,":[146],"propose":[148],"selection":[150,170],"terms,":[154],"Nystr\\\"om":[161,176],"approximate":[164],"term-term":[166,211],"matrix.":[168],"The":[169],"is":[178],"performed":[179],"randomly":[181],"sampling":[182],"probabilities":[185],"proportional":[186],"lengths":[189],"vectors":[192],"space.":[196],"This":[197],"allows":[198],"more":[199,204],"important":[200],"influence":[205],"on":[206],"approximation":[208],"matrix":[213],"accordingly":[215],"achieves":[216],"better":[217],"accuracy.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}