{"id":"https://openalex.org/W1985615910","doi":"https://doi.org/10.1145/1553374.1553410","title":"Accounting for burstiness in topic models","display_name":"Accounting for burstiness in topic models","publication_year":2009,"publication_date":"2009-06-14","ids":{"openalex":"https://openalex.org/W1985615910","doi":"https://doi.org/10.1145/1553374.1553410","mag":"1985615910"},"language":"en","primary_location":{"id":"doi:10.1145/1553374.1553410","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","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/A5068995048","display_name":"Gabriel Doyle","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":"Gabriel Doyle","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":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":6.0903,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.97183099,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"281","last_page":"288"},"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":0.9984999895095825,"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":0.9951000213623047,"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":0.9827414155006409},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.8943688869476318},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7482737898826599},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7325578331947327},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.5326870083808899},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5234255790710449},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5067554116249084},{"id":"https://openalex.org/keywords/dirichlet-distribution","display_name":"Dirichlet distribution","score":0.48673108220100403},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.48097527027130127},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46932098269462585},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45659148693084717},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4346461892127991},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4176921844482422},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.22733044624328613},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.21743586659431458},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16286712884902954}],"concepts":[{"id":"https://openalex.org/C2781023610","wikidata":"https://www.wikidata.org/wiki/Q17006304","display_name":"Burstiness","level":3,"score":0.9827414155006409},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.8943688869476318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7482737898826599},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7325578331947327},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.5326870083808899},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5234255790710449},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5067554116249084},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.48673108220100403},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.48097527027130127},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46932098269462585},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45659148693084717},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4346461892127991},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4176921844482422},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.22733044624328613},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.21743586659431458},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16286712884902954},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"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/C182310444","wikidata":"https://www.wikidata.org/wiki/Q1332643","display_name":"Boundary value problem","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1553374.1553410","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1553374.1553410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th Annual International Conference on Machine Learning","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.149.5963","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.149.5963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~icml2009/papers/162.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.153.2096","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.153.2096","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/TopicBurstiness.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G2572144590","display_name":"Language, Communication and the Brain","funder_award_id":"5t32dc000041-17","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"}],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1638753340","https://openalex.org/W1847878629","https://openalex.org/W1880262756","https://openalex.org/W2001082470","https://openalex.org/W2005126631","https://openalex.org/W2025653016","https://openalex.org/W2050341350","https://openalex.org/W2096814070","https://openalex.org/W2106490775","https://openalex.org/W2107034620","https://openalex.org/W2110591510","https://openalex.org/W2112050062","https://openalex.org/W2112971401","https://openalex.org/W2135631383","https://openalex.org/W2140336868","https://openalex.org/W2151780865","https://openalex.org/W2166468440","https://openalex.org/W4238346259"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3005513013","https://openalex.org/W2611137333","https://openalex.org/W4291700620","https://openalex.org/W4317422773"],"abstract_inverted_index":{"Many":[0],"different":[1],"topic":[2,16,64,106],"models":[3,17,107],"have":[4],"been":[5],"used":[6,48,59],"successfully":[7],"for":[8],"a":[9,38,45,51,63],"variety":[10],"of":[11,30,41],"applications.":[12],"However,":[13],"even":[14],"state-of-the-art":[15],"suffer":[18],"from":[19],"the":[20,28,84,102],"important":[21],"flaw":[22],"that":[23,43,66,108],"they":[24],"do":[25],"not":[26],"capture":[27],"tendency":[29],"words":[31],"to":[32,57,73,100],"appear":[33],"in":[34,50],"bursts;":[35],"it":[36,53],"is":[37,47,54,98],"fundamental":[39],"property":[40],"language":[42],"if":[44],"word":[46],"once":[49],"document,":[52],"more":[55,110],"likely":[56],"be":[58],"again.":[60],"We":[61],"introduce":[62],"model":[65,74,86],"uses":[67],"Dirichlet":[68,94],"compound":[69],"multinomial":[70],"(DCM)":[71],"distributions":[72],"this":[75],"burstiness":[76],"phenomenon.":[77],"On":[78],"both":[79],"text":[80],"and":[81],"non-text":[82],"datasets,":[83],"new":[85],"achieves":[87],"better":[88],"held-out":[89],"likelihood":[90],"than":[91,112],"standard":[92],"latent":[93],"allocation":[95],"(LDA).":[96],"It":[97],"straightforward":[99],"incorporate":[101],"DCM":[103],"extension":[104],"into":[105],"are":[109],"complex":[111],"LDA.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":11},{"year":2012,"cited_by_count":8}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}