{"id":"https://openalex.org/W2135631383","doi":"https://doi.org/10.1145/1102351.1102420","title":"Modeling word burstiness using the Dirichlet distribution","display_name":"Modeling word burstiness using the Dirichlet distribution","publication_year":2005,"publication_date":"2005-01-01","ids":{"openalex":"https://openalex.org/W2135631383","doi":"https://doi.org/10.1145/1102351.1102420","mag":"2135631383"},"language":"en","primary_location":{"id":"doi:10.1145/1102351.1102420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning - ICML '05","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/A5049279492","display_name":"Rasmus Elsborg Madsen","orcid":null},"institutions":[{"id":"https://openalex.org/I96673099","display_name":"Technical University of Denmark","ror":"https://ror.org/04qtj9h94","country_code":"DK","type":"education","lineage":["https://openalex.org/I96673099"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Rasmus E. Madsen","raw_affiliation_strings":["#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"#N##TAB##TAB##TAB##TAB# Technical University of Denmark#N##TAB##TAB##TAB#","institution_ids":["https://openalex.org/I96673099"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089892601","display_name":"David Kauchak","orcid":"https://orcid.org/0000-0002-5208-634X"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kauchak","raw_affiliation_strings":["University of California; San Diego La Jolla CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California; San Diego La Jolla CA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038246567","display_name":"Charles Elkan","orcid":null},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Elkan","raw_affiliation_strings":["University of California; San Diego La Jolla CA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California; San Diego La Jolla CA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.8724,"has_fulltext":false,"cited_by_count":284,"citation_normalized_percentile":{"value":0.98346492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"545","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9994999766349792,"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":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9980000257492065,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9951000213623047,"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/burstiness","display_name":"Burstiness","score":0.964111328125},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.694513738155365},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5281360745429993},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5127635598182678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4463568329811096},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40907418727874756},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17109784483909607},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.14701604843139648}],"concepts":[{"id":"https://openalex.org/C2781023610","wikidata":"https://www.wikidata.org/wiki/Q17006304","display_name":"Burstiness","level":3,"score":0.964111328125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.694513738155365},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5281360745429993},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5127635598182678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4463568329811096},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40907418727874756},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17109784483909607},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.14701604843139648},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/1102351.1102420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1102351.1102420","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd international conference on Machine learning - ICML '05","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.5134","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.5134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://eprints.pascal-network.org/archive/00001454/01/dcmnbV10.1.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.80.2934","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.80.2934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-cse.ucsd.edu/~elkan/icml2005.pdf","raw_type":"text"},{"id":"pmh:oai:pure.atira.dk:Publications/5891f05d-5070-4162-b7a8-6d981623f9c4","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":""},{"id":"pmh:oai:pure.atira.dk:publications/5891f05d-5070-4162-b7a8-6d981623f9c4","is_oa":false,"landing_page_url":"https://orbit.dtu.dk/en/publications/5891f05d-5070-4162-b7a8-6d981623f9c4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400705","display_name":"Technical University of Denmark, DTU Orbit (Technical University of Denmark, DTU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I96673099","host_organization_name":"Technical University of Denmark","host_organization_lineage":["https://openalex.org/I96673099"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Madsen , R E , Kauchak , D & Elkan , C 2005 , Modeling Word Burstiness Using the Dirichlet Distribution . in International Conference on Machine Learning . pp. 489-498 . < http://www2.imm.dtu.dk/pubdb/p.php?3996 >","raw_type":"contributionToPeriodical"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.8100000023841858,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W190008395","https://openalex.org/W1550206324","https://openalex.org/W1880262756","https://openalex.org/W1924689489","https://openalex.org/W2094934653","https://openalex.org/W2101746535","https://openalex.org/W2107743791","https://openalex.org/W2108903064","https://openalex.org/W2113110240","https://openalex.org/W2118020653","https://openalex.org/W2121182452","https://openalex.org/W2140336868","https://openalex.org/W2144211451","https://openalex.org/W2147152072","https://openalex.org/W2165612380","https://openalex.org/W2321470647"],"related_works":["https://openalex.org/W1843717240","https://openalex.org/W2340440348","https://openalex.org/W2508200300","https://openalex.org/W2737070158","https://openalex.org/W4297850514","https://openalex.org/W2138256111","https://openalex.org/W2495822618","https://openalex.org/W1591572210","https://openalex.org/W1906989185","https://openalex.org/W3192589309"],"abstract_inverted_index":{"Multinomial":[0],"distributions":[1],"are":[2],"often":[3],"used":[4],"to":[5,23,36,53,68,102,113,120],"model":[6,48,58],"text":[7,85],"documents.":[8],"However,":[9],"they":[10],"do":[11],"not":[12],"capture":[13,69],"well":[14],"the":[15,44,54,75,81,99,106,121],"phenomenon":[16],"that":[17,74,98,114],"words":[18],"in":[19,25],"a":[20,28],"document":[21,96],"tend":[22],"appear":[24,37],"bursts:":[26],"if":[27],"word":[29],"appears":[30],"once,":[31],"it":[32,67],"is":[33,77,111],"more":[34],"likely":[35],"again.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"propose":[43],"Dirichlet":[45],"compound":[46],"multinomial":[47,82,107,122],"(DCM)":[49],"as":[50],"an":[51],"alternative":[52],"multinomial.":[55],"The":[56],"DCM":[57,76,100,109],"has":[59],"one":[60],"additional":[61],"degree":[62],"of":[63],"freedom,":[64],"which":[65],"allows":[66],"burstiness.":[70],"We":[71,90],"show":[72,92],"experimentally":[73],"substantially":[78],"better":[79,103],"than":[80,105],"at":[83],"modeling":[84],"data,":[86],"measured":[87],"by":[88],"perplexity.":[89],"also":[91],"using":[93],"three":[94],"standard":[95],"collections":[97],"leads":[101],"classification":[104],"model.":[108,123],"performance":[110],"comparable":[112],"obtained":[115],"with":[116],"multiple":[117],"heuristic":[118],"changes":[119],"1.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":20},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":13},{"year":2017,"cited_by_count":12},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":17},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":19}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}