{"id":"https://openalex.org/W3111251828","doi":"https://doi.org/10.1007/s11222-020-09989-9","title":"Deep mixtures of unigrams for uncovering topics in textual data","display_name":"Deep mixtures of unigrams for uncovering topics in textual data","publication_year":2021,"publication_date":"2021-03-03","ids":{"openalex":"https://openalex.org/W3111251828","doi":"https://doi.org/10.1007/s11222-020-09989-9","mag":"3111251828"},"language":"en","primary_location":{"id":"doi:10.1007/s11222-020-09989-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11222-020-09989-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11222-020-09989-9.pdf","source":{"id":"https://openalex.org/S5437875","display_name":"Statistics and Computing","issn_l":"0960-3174","issn":["0960-3174","1573-1375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistics and Computing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11222-020-09989-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051054730","display_name":"Cinzia Viroli","orcid":"https://orcid.org/0000-0002-3278-5266"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Cinzia Viroli","raw_affiliation_strings":["Department of Statistical Sciences, University of Bologna, via Belle Arti 41, 40126, Bologna, Italy","University of Bologna"],"raw_orcid":"https://orcid.org/0000-0002-3278-5266","affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Bologna, via Belle Arti 41, 40126, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"University of Bologna","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060308577","display_name":"Laura Anderlucci","orcid":"https://orcid.org/0000-0003-1161-6145"},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Laura Anderlucci","raw_affiliation_strings":["Department of Statistical Sciences, University of Bologna, via Belle Arti 41, 40126, Bologna, Italy","Department of Statistical Sciences , University of Bologna , Bologna, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistical Sciences, University of Bologna, via Belle Arti 41, 40126, Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]},{"raw_affiliation_string":"Department of Statistical Sciences , University of Bologna , Bologna, Italy","institution_ids":["https://openalex.org/I9360294"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5051054730"],"corresponding_institution_ids":["https://openalex.org/I9360294"],"apc_list":{"value":2690,"currency":"USD","value_usd":2690},"apc_paid":{"value":2690,"currency":"USD","value_usd":2690},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.01124208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","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"}},"topics":[{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","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":0.9983999729156494,"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/T10637","display_name":"Advanced Clustering Algorithms Research","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7963690757751465},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6977301836013794},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6244136095046997},{"id":"https://openalex.org/keywords/medoid","display_name":"Medoid","score":0.5957505106925964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5246313214302063},{"id":"https://openalex.org/keywords/rand-index","display_name":"Rand index","score":0.492511123418808},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46784600615501404},{"id":"https://openalex.org/keywords/spectral-clustering","display_name":"Spectral clustering","score":0.45370975136756897},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.45351189374923706},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.4294452667236328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4215783476829529},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.32292893528938293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7963690757751465},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6977301836013794},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6244136095046997},{"id":"https://openalex.org/C63085389","wikidata":"https://www.wikidata.org/wiki/Q4287912","display_name":"Medoid","level":3,"score":0.5957505106925964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246313214302063},{"id":"https://openalex.org/C111442797","wikidata":"https://www.wikidata.org/wiki/Q7291446","display_name":"Rand index","level":3,"score":0.492511123418808},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46784600615501404},{"id":"https://openalex.org/C105611402","wikidata":"https://www.wikidata.org/wiki/Q2976589","display_name":"Spectral clustering","level":3,"score":0.45370975136756897},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.45351189374923706},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4294452667236328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4215783476829529},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.32292893528938293}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1007/s11222-020-09989-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11222-020-09989-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11222-020-09989-9.pdf","source":{"id":"https://openalex.org/S5437875","display_name":"Statistics and Computing","issn_l":"0960-3174","issn":["0960-3174","1573-1375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistics and Computing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1902.06615","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1902.06615","pdf_url":"https://arxiv.org/pdf/1902.06615","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3111251828","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1902.06615v2","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1902.06615","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1902.06615","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1007/s11222-020-09989-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11222-020-09989-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11222-020-09989-9.pdf","source":{"id":"https://openalex.org/S5437875","display_name":"Statistics and Computing","issn_l":"0960-3174","issn":["0960-3174","1573-1375"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Statistics and Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3111251828.pdf","grobid_xml":"https://content.openalex.org/works/W3111251828.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1507070875","https://openalex.org/W1579271636","https://openalex.org/W1880262756","https://openalex.org/W1884731728","https://openalex.org/W1996640618","https://openalex.org/W2001082470","https://openalex.org/W2011832962","https://openalex.org/W2040729282","https://openalex.org/W2049017883","https://openalex.org/W2049633694","https://openalex.org/W2076063813","https://openalex.org/W2079623157","https://openalex.org/W2097089247","https://openalex.org/W2110632824","https://openalex.org/W2127939112","https://openalex.org/W2129250947","https://openalex.org/W2134507164","https://openalex.org/W2148464528","https://openalex.org/W2150593711","https://openalex.org/W2162478474","https://openalex.org/W2165232124","https://openalex.org/W2165874743","https://openalex.org/W2169694221","https://openalex.org/W2308181013","https://openalex.org/W2314008914","https://openalex.org/W2488678869","https://openalex.org/W2768611535","https://openalex.org/W2799787995","https://openalex.org/W2809034148","https://openalex.org/W2919115771","https://openalex.org/W2953106669","https://openalex.org/W2963083182","https://openalex.org/W4235169531","https://openalex.org/W6743145398"],"related_works":["https://openalex.org/W3135844644","https://openalex.org/W311731905","https://openalex.org/W2157512230","https://openalex.org/W2974786925","https://openalex.org/W2158312129","https://openalex.org/W2109622481","https://openalex.org/W2589464479","https://openalex.org/W2089347563","https://openalex.org/W2558497900","https://openalex.org/W2971510218","https://openalex.org/W593633726","https://openalex.org/W2426729591","https://openalex.org/W2274398059","https://openalex.org/W3111156014","https://openalex.org/W1927855281","https://openalex.org/W2148744937","https://openalex.org/W1990694217","https://openalex.org/W2418423341","https://openalex.org/W2951071850","https://openalex.org/W2159160619"],"abstract_inverted_index":{"Abstract":[0],"Mixtures":[1],"of":[2,6,30,74,76,82,90,111,115,122,150,169,188],"unigrams":[3,77,116,170],"are":[4],"one":[5],"the":[7,24,37,46,63,79,101,112,173,213],"simplest":[8],"and":[9,51,125,178,193,199],"most":[10],"efficient":[11],"tools":[12],"for":[13,78,94],"clustering":[14,157,177,208],"textual":[15],"data,":[16,155],"as":[17,44],"they":[18],"assume":[19],"that":[20,121,204],"documents":[21,85],"related":[22],"to":[23,143,159],"same":[25],"topic":[26],"have":[27],"similar":[28],"distributions":[29],"terms,":[31,91],"naturally":[32],"described":[33],"by":[34,92],"multinomials.":[35],"When":[36],"classification":[38,81,191,214],"task":[39],"is":[40,49,103,117,184],"particularly":[41],"challenging,":[42],"such":[43,209],"when":[45],"document-term":[47],"matrix":[48],"high-dimensional":[50],"extremely":[52],"sparse,":[53],"a":[54,71,87,106],"more":[55],"composite":[56],"representation":[57],"can":[58],"provide":[59],"better":[60],"insight":[61],"into":[62],"grouping":[64],"structure.":[65],"In":[66],"this":[67],"work,":[68],"we":[69],"developed":[70],"deep":[72,113,206],"version":[73],"mixtures":[75,114,168],"unsupervised":[80],"very":[83],"short":[84],"with":[86,96,120,131,136,162],"large":[88],"number":[89],"allowing":[93],"models":[95],"further":[97],"deeper":[98],"latent":[99,165],"layers;":[100],"proposal":[102],"derived":[104],"in":[105,186,207],"Bayesian":[107],"framework.":[108],"The":[109,182],"behavior":[110],"empirically":[118],"compared":[119],"other":[123],"traditional":[124],"state-of-the-art":[126],"methods,":[127],"namely":[128],"k":[129,134],"-means":[130,135],"cosine":[132,163],"distance,":[133],"Euclidean":[137],"distance":[138],"on":[139,152],"data":[140,201,210],"transformed":[141,154],"according":[142,158],"semantic":[144],"analysis,":[145],"partition":[146],"around":[147],"medoids,":[148],"mixture":[149],"Gaussians":[151],"semantic-based":[153],"hierarchical":[156],"Ward\u2019s":[160],"method":[161],"dissimilarity,":[164],"Dirichlet":[166],"allocation,":[167],"estimated":[171],"via":[172],"EM":[174],"algorithm,":[175],"spectral":[176],"affinity":[179],"propagation":[180],"clustering.":[181],"performance":[183],"evaluated":[185],"terms":[187],"both":[189],"correct":[190],"rate":[192],"Adjusted":[194],"Rand":[195],"Index.":[196],"Simulation":[197],"studies":[198],"real":[200],"analysis":[202],"prove":[203],"going":[205],"highly":[211],"improves":[212],"accuracy.":[215]},"counts_by_year":[],"updated_date":"2026-08-11T07:18:39.950985","created_date":"2025-10-10T00:00:00"}