{"id":"https://openalex.org/W2100626830","doi":"https://doi.org/10.1145/1645953.1646170","title":"Text segmentation via topic modeling","display_name":"Text segmentation via topic modeling","publication_year":2009,"publication_date":"2009-11-02","ids":{"openalex":"https://openalex.org/W2100626830","doi":"https://doi.org/10.1145/1645953.1646170","mag":"2100626830"},"language":"en","primary_location":{"id":"doi:10.1145/1645953.1646170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th 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/A5017720802","display_name":"Hemant Misra","orcid":"https://orcid.org/0000-0002-8179-4441"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Hemant Misra","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom","University of Glasgow, Glasgow, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom#TAB#","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030615769","display_name":"Fran\u00e7ois Yvon","orcid":"https://orcid.org/0000-0002-7972-7442"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I4210115485","display_name":"Laboratoire d'Informatique pour la M\u00e9canique et les Sciences de l'Ing\u00e9nieur","ror":"https://ror.org/01raq4x89","country_code":"FR","type":"facility","lineage":["https://openalex.org/I102197404","https://openalex.org/I1294671590","https://openalex.org/I4210115485","https://openalex.org/I4210159245"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fran\u00e7ois Yvon","raw_affiliation_strings":["University Paris-Sud and LIMSI-CNRS, Orsay, France","University Paris-Sud and LIMSI-CNRS, Orsay, France#TAB#"],"affiliations":[{"raw_affiliation_string":"University Paris-Sud and LIMSI-CNRS, Orsay, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I4210115485","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"University Paris-Sud and LIMSI-CNRS, Orsay, France#TAB#","institution_ids":["https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069702331","display_name":"Joemon M. Jose","orcid":"https://orcid.org/0000-0001-9228-1759"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Joemon M. Jose","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom","University of Glasgow, Glasgow, United Kingdom#TAB#"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom#TAB#","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5105628617","display_name":"Olivier Capp\u00e9","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Cappe","raw_affiliation_strings":["TELECOM ParisTech and LTCI/CNRS, Paris, France","Telecom ParisTech and LTCI-CNRS, Paris (France)"],"affiliations":[{"raw_affiliation_string":"TELECOM ParisTech and LTCI/CNRS, Paris, France","institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Telecom ParisTech and LTCI-CNRS, Paris (France)","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I1294671590","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017720802"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":9.5959,"has_fulltext":false,"cited_by_count":88,"citation_normalized_percentile":{"value":0.98104794,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1553","last_page":"1556"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T10181","display_name":"Natural Language Processing Techniques","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":0.9976000189781189,"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/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.9449454545974731},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.8220601081848145},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8079075813293457},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7243131995201111},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6878384947776794},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.597289502620697},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5868074893951416},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5461673140525818},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.54352205991745},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5297437906265259},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48837822675704956},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.44965294003486633},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.435888409614563},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4242074489593506},{"id":"https://openalex.org/keywords/hierarchical-dirichlet-process","display_name":"Hierarchical Dirichlet process","score":0.41848036646842957},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38833123445510864},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0999796986579895}],"concepts":[{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.9449454545974731},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.8220601081848145},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8079075813293457},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7243131995201111},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6878384947776794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.597289502620697},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5868074893951416},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5461673140525818},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.54352205991745},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5297437906265259},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48837822675704956},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.44965294003486633},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.435888409614563},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4242074489593506},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.41848036646842957},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38833123445510864},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0999796986579895},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1645953.1646170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1645953.1646170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:39529","is_oa":false,"landing_page_url":"http://eprints.gla.ac.uk/39529/","pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":false,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W170853248","https://openalex.org/W1488461535","https://openalex.org/W1557074680","https://openalex.org/W1604285433","https://openalex.org/W1626945812","https://openalex.org/W1828401780","https://openalex.org/W1880262756","https://openalex.org/W1977434113","https://openalex.org/W2001082470","https://openalex.org/W2018627475","https://openalex.org/W2080179128","https://openalex.org/W2144946252","https://openalex.org/W2148818577","https://openalex.org/W2150102617","https://openalex.org/W2166490638","https://openalex.org/W2603454388","https://openalex.org/W2613433911","https://openalex.org/W6629169963","https://openalex.org/W6639619044"],"related_works":["https://openalex.org/W2914864478","https://openalex.org/W2008338582","https://openalex.org/W2097627380","https://openalex.org/W1999586157","https://openalex.org/W2891616219","https://openalex.org/W2796920963","https://openalex.org/W4291700620","https://openalex.org/W3204672119","https://openalex.org/W22044811","https://openalex.org/W2625329765"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"the":[3,17,38,45,50,87],"task":[4],"of":[5,19,37,60,86],"text":[6,29],"segmentation":[7],"is":[8,41,59],"approached":[9],"from":[10],"a":[11,28,75,92],"topic":[12,24,51],"modeling":[13],"perspective.":[14],"We":[15],"investigate":[16],"use":[18,62],"latent":[20],"Dirichlet":[21],"allocation":[22],"(LDA)":[23],"model":[25],"to":[26],"segment":[27,46,66],"into":[30],"semantically":[31],"coherent":[32],"segments.":[33],"A":[34],"major":[35],"benefit":[36],"proposed":[39],"approach":[40,73],"that":[42],"along":[43],"with":[44,54],"boundaries,":[47],"it":[48],"outputs":[49],"distribution":[52],"associated":[53],"each":[55],"segment.":[56],"This":[57],"information":[58],"potential":[61],"in":[63],"applications":[64],"like":[65],"retrieval":[67],"and":[68,79],"discourse":[69],"analysis.":[70],"The":[71],"new":[72],"outperforms":[74],"standard":[76],"baseline":[77],"method":[78],"yields":[80],"significantly":[81],"better":[82],"performance":[83],"than":[84],"most":[85],"available":[88],"unsupervised":[89],"methods":[90],"on":[91],"benchmark":[93],"dataset.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}