{"id":"https://openalex.org/W2021378816","doi":"https://doi.org/10.1002/meet.14504901209","title":"Enriching text representation with frequent pattern mining for probabilistic topic modeling","display_name":"Enriching text representation with frequent pattern mining for probabilistic topic modeling","publication_year":2012,"publication_date":"2012-01-01","ids":{"openalex":"https://openalex.org/W2021378816","doi":"https://doi.org/10.1002/meet.14504901209","mag":"2021378816"},"language":"en","primary_location":{"id":"doi:10.1002/meet.14504901209","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.14504901209","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.14504901209","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.14504901209","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110134285","display_name":"Hyun Duk Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hyun Duk Kim","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103448879","display_name":"Dae Hoon Park","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Dae Hoon Park","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031868292","display_name":"Yue Lu","orcid":"https://orcid.org/0000-0003-4062-6553"},"institutions":[{"id":"https://openalex.org/I113979032","display_name":"Twitter (United States)","ror":"https://ror.org/04wt43v05","country_code":"US","type":"company","lineage":["https://openalex.org/I113979032"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yue Lu","raw_affiliation_strings":["University of Illinois at Twitter Inc"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Twitter Inc","institution_ids":["https://openalex.org/I113979032"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108648432","display_name":"ChengXiang Zhai","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"ChengXiang Zhai","raw_affiliation_strings":["University of Illinois at Urbana-Champaign","University of Illinois at Urbana Champaign"],"affiliations":[{"raw_affiliation_string":"University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois at Urbana Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031868292","https://openalex.org/A5103448879","https://openalex.org/A5108648432","https://openalex.org/A5110134285"],"corresponding_institution_ids":["https://openalex.org/I113979032","https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":12.4781,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.98288139,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"49","issue":"1","first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9987000226974487,"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":0.9979000091552734,"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":0.8137714266777039},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7102056741714478},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.683918833732605},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6399503350257874},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6368246078491211},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.6161552667617798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6054288744926453},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5842846035957336},{"id":"https://openalex.org/keywords/bag-of-words-model","display_name":"Bag-of-words model","score":0.47489133477211},{"id":"https://openalex.org/keywords/probabilistic-latent-semantic-analysis","display_name":"Probabilistic latent semantic analysis","score":0.4667420983314514},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4609667956829071},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37920573353767395},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07580769062042236}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8137714266777039},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7102056741714478},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.683918833732605},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6399503350257874},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6368246078491211},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.6161552667617798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6054288744926453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5842846035957336},{"id":"https://openalex.org/C13672336","wikidata":"https://www.wikidata.org/wiki/Q3460803","display_name":"Bag-of-words model","level":2,"score":0.47489133477211},{"id":"https://openalex.org/C112933361","wikidata":"https://www.wikidata.org/wiki/Q2845258","display_name":"Probabilistic latent semantic analysis","level":2,"score":0.4667420983314514},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4609667956829071},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37920573353767395},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07580769062042236},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/meet.14504901209","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.14504901209","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.14504901209","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1002/meet.14504901209","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.14504901209","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.14504901209","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6800000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332222","display_name":"University of Illinois at Urbana-Champaign","ror":"https://ror.org/047426m28"},{"id":"https://openalex.org/F4320333591","display_name":"Multidisciplinary University Research Initiative","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2021378816.pdf","grobid_xml":"https://content.openalex.org/works/W2021378816.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W110175884","https://openalex.org/W1506285740","https://openalex.org/W1537336823","https://openalex.org/W1585646276","https://openalex.org/W1608194207","https://openalex.org/W1641039719","https://openalex.org/W1676985236","https://openalex.org/W1880262756","https://openalex.org/W1993309640","https://openalex.org/W2001082470","https://openalex.org/W2020999234","https://openalex.org/W2030969394","https://openalex.org/W2033593667","https://openalex.org/W2037965136","https://openalex.org/W2042980227","https://openalex.org/W2049633694","https://openalex.org/W2064853889","https://openalex.org/W2094951132","https://openalex.org/W2096110600","https://openalex.org/W2098062695","https://openalex.org/W2104210067","https://openalex.org/W2104924585","https://openalex.org/W2107743791","https://openalex.org/W2108420397","https://openalex.org/W2110723042","https://openalex.org/W2112050062","https://openalex.org/W2117169652","https://openalex.org/W2123571359","https://openalex.org/W2129294185","https://openalex.org/W2130978632","https://openalex.org/W2132827946","https://openalex.org/W2138323616","https://openalex.org/W2147694185","https://openalex.org/W2154970197","https://openalex.org/W2155358700","https://openalex.org/W2160407462","https://openalex.org/W2169606435","https://openalex.org/W2171836785","https://openalex.org/W2952148308","https://openalex.org/W4233135949","https://openalex.org/W4237791300","https://openalex.org/W4252403066","https://openalex.org/W4254829975"],"related_works":["https://openalex.org/W2921491680","https://openalex.org/W2082325506","https://openalex.org/W2982493961","https://openalex.org/W2784194212","https://openalex.org/W2251863249","https://openalex.org/W2132052677","https://openalex.org/W2087743880","https://openalex.org/W4365211920","https://openalex.org/W4291700620","https://openalex.org/W3014948380"],"abstract_inverted_index":{"Abstract":[0],"Probabilistic":[1],"topic":[2,18,65,102,143,151,180,195],"models":[3,19,144,152,181],"have":[4,20],"been":[5,21],"proven":[6],"very":[7],"useful":[8],"for":[9,64,108,131,141,182],"many":[10,15],"text":[11,33,111],"mining":[12,71,132],"tasks.":[13],"Although":[14],"variants":[16],"of":[17,32,48,159,190],"proposed,":[22],"most":[23],"existing":[24,178],"works":[25],"are":[26,40,136],"based":[27],"on":[28],"the":[29,61,95,117,156,160,183],"bag\u2010of\u2010words":[30,62,97,118],"representation":[31,47,63],"in":[34,44,194],"which":[35],"word":[36,75,134],"combination":[37],"and":[38,84,197,202],"order":[39],"generally":[41],"ignored,":[42],"resulting":[43],"inaccurate":[45],"semantic":[46,80,91,124],"text.":[49],"In":[50],"this":[51,138],"paper,":[52],"we":[53,113],"propose":[54],"a":[55,101,105,167],"general":[56,139],"way":[57],"to":[58,72,93,120,148],"go":[59,115],"beyond":[60,116],"modeling":[66,196],"by":[67],"applying":[68],"frequent":[69,74,133,168,191],"pattern":[70,192],"discover":[73],"patterns":[76,135,204],"that":[77,165,199],"can":[78,114,145,173],"capture":[79,122],"associations":[81,125],"between":[82,126],"words":[83],"then":[85],"using":[86,200],"them":[87],"as":[88,104],"additional":[89],"supplementary":[90],"units":[92],"augment":[94],"conventional":[96],"representation.":[98],"By":[99],"viewing":[100],"model":[103,107],"generative":[106],"such":[109,166],"augmented":[110],"data,":[112],"assumption":[119],"potentially":[121],"more":[123],"words.":[127],"Since":[128],"efficient":[129],"algorithms":[130],"available,":[137],"strategy":[140],"improving":[142],"be":[146],"applied":[147],"improve":[149,174],"any":[150],"without":[153],"substantially":[154],"increasing":[155],"computational":[157],"complexity":[158],"model.":[161],"Experiment":[162],"results":[163],"show":[164],"pattern\u2010based":[169],"data":[170],"enrichment":[171],"approach":[172],"over":[175],"two":[176],"representative":[177],"probabilistic":[179],"classification":[184],"task.":[185],"We":[186],"also":[187],"studied":[188],"variations":[189],"usage":[193],"found":[198],"compressed":[201],"closed":[203],"performs":[205],"best.":[206]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":4}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}