{"id":"https://openalex.org/W4229019131","doi":"https://doi.org/10.3390/info13020057","title":"Knowledge Source Rankings for Semi-Supervised Topic Modeling","display_name":"Knowledge Source Rankings for Semi-Supervised Topic Modeling","publication_year":2022,"publication_date":"2022-01-24","ids":{"openalex":"https://openalex.org/W4229019131","doi":"https://doi.org/10.3390/info13020057"},"language":"en","primary_location":{"id":"doi:10.3390/info13020057","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info13020057","pdf_url":"https://www.mdpi.com/2078-2489/13/2/57/pdf?version=1643014941","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2078-2489/13/2/57/pdf?version=1643014941","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027420297","display_name":"Justin N. Wood","orcid":"https://orcid.org/0000-0002-8383-024X"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Justin Wood","raw_affiliation_strings":["Deparment of Computer Science, University of California, Los Angeles, CA 90095, USA"],"affiliations":[{"raw_affiliation_string":"Deparment of Computer Science, University of California, Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001751044","display_name":"Corey Arnold","orcid":"https://orcid.org/0000-0002-4119-8143"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Corey Arnold","raw_affiliation_strings":["Deparment of Computer Science, University of California, Los Angeles, CA 90095, USA"],"affiliations":[{"raw_affiliation_string":"Deparment of Computer Science, University of California, Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100392089","display_name":"Wei Wang","orcid":"https://orcid.org/0000-0002-8180-2886"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Wang","raw_affiliation_strings":["Deparment of Computer Science, University of California, Los Angeles, CA 90095, USA"],"affiliations":[{"raw_affiliation_string":"Deparment of Computer Science, University of California, Los Angeles, CA 90095, USA","institution_ids":["https://openalex.org/I161318765"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5027420297"],"corresponding_institution_ids":["https://openalex.org/I161318765"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.1326,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.5024713,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"13","issue":"2","first_page":"57","last_page":"57"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998999834060669,"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":0.9998999834060669,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9969000220298767,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9961000084877014,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.9080058336257935},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.8602695465087891},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7971396446228027},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7869594097137451},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7318837642669678},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.7260873317718506},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5745055079460144},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5085850954055786},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48031941056251526},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47704094648361206},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4750552177429199},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4749320149421692},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.4683959484100342},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.46681734919548035},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37993115186691284},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.376320481300354},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3397572636604309}],"concepts":[{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.9080058336257935},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8602695465087891},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7971396446228027},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7869594097137451},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7318837642669678},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.7260873317718506},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5745055079460144},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5085850954055786},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48031941056251526},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47704094648361206},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4750552177429199},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4749320149421692},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.4683959484100342},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.46681734919548035},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37993115186691284},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.376320481300354},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3397572636604309},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/info13020057","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info13020057","pdf_url":"https://www.mdpi.com/2078-2489/13/2/57/pdf?version=1643014941","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7348b0637b764d3d9081464348ccc4f1","is_oa":true,"landing_page_url":"https://doaj.org/article/7348b0637b764d3d9081464348ccc4f1","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information, Vol 13, Iss 2, p 57 (2022)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2078-2489/13/2/57/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/info13020057","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Information; Volume 13; Issue 2; Pages: 57","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/info13020057","is_oa":true,"landing_page_url":"https://doi.org/10.3390/info13020057","pdf_url":"https://www.mdpi.com/2078-2489/13/2/57/pdf?version=1643014941","source":{"id":"https://openalex.org/S4210219776","display_name":"Information","issn_l":"2078-2489","issn":["2078-2489"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Information","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4229019131.pdf","grobid_xml":"https://content.openalex.org/works/W4229019131.grobid-xml"},"referenced_works_count":56,"referenced_works":["https://openalex.org/W1506246224","https://openalex.org/W1673310716","https://openalex.org/W1854214752","https://openalex.org/W1969486090","https://openalex.org/W1973515220","https://openalex.org/W2001082470","https://openalex.org/W2006394056","https://openalex.org/W2018844855","https://openalex.org/W2030903088","https://openalex.org/W2042380438","https://openalex.org/W2063023883","https://openalex.org/W2097807612","https://openalex.org/W2102733276","https://openalex.org/W2113855231","https://openalex.org/W2122683976","https://openalex.org/W2153579005","https://openalex.org/W2159426623","https://openalex.org/W2170344111","https://openalex.org/W2174344915","https://openalex.org/W2174706414","https://openalex.org/W2207653751","https://openalex.org/W2252024428","https://openalex.org/W2788595985","https://openalex.org/W2888039742","https://openalex.org/W2903941565","https://openalex.org/W2914379972","https://openalex.org/W2963211364","https://openalex.org/W2998186405","https://openalex.org/W3039777472","https://openalex.org/W3046777012","https://openalex.org/W3086232233","https://openalex.org/W3086904738","https://openalex.org/W3087374654","https://openalex.org/W3094287898","https://openalex.org/W3116424773","https://openalex.org/W3118810629","https://openalex.org/W3129095573","https://openalex.org/W3134447942","https://openalex.org/W3157310275","https://openalex.org/W3157927033","https://openalex.org/W3166574703","https://openalex.org/W3170618480","https://openalex.org/W3171661673","https://openalex.org/W3172132431","https://openalex.org/W3174530819","https://openalex.org/W3177067286","https://openalex.org/W3208604769","https://openalex.org/W4207041109","https://openalex.org/W4231510805","https://openalex.org/W4246803012","https://openalex.org/W4252036160","https://openalex.org/W6631501603","https://openalex.org/W6639619044","https://openalex.org/W6685091216","https://openalex.org/W6791004676","https://openalex.org/W6833425917"],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W4293734197","https://openalex.org/W2252095989","https://openalex.org/W4322096525","https://openalex.org/W2551914602","https://openalex.org/W4281893144","https://openalex.org/W2105076537","https://openalex.org/W2787311093","https://openalex.org/W2169401934","https://openalex.org/W2921174581"],"abstract_inverted_index":{"Recent":[0],"work":[1],"suggests":[2],"knowledge":[3,21,76,100,138,150,210],"sources":[4,22,77],"can":[5,171,187],"be":[6,80],"added":[7],"into":[8],"the":[9,61,72,75,83,89,115,127,143,155,160,180],"topic":[10,18,34,43,111,119,205,218,226,244],"modeling":[11],"process":[12],"to":[13,48,70,79,124,141,158,197],"label":[14],"topics":[15,50,140],"and":[16,191,201,247],"improve":[17,189],"discovery.":[19],"The":[20,92],"typically":[23],"consist":[24],"of":[25,28,55,117,136,162],"a":[26,33,46,53,56,134,149,214,221,228,233,240,248],"collection":[27],"human-constructed":[29],"articles,":[30],"each":[31],"describing":[32],"(article-topic)":[35],"for":[36,108],"an":[37,163],"entire":[38],"domain.":[39,57],"However,":[40],"these":[41],"semisupervised":[42,118,204],"models":[44],"assume":[45],"corpus":[47],"contain":[49],"on":[51,154],"only":[52],"subset":[54],"Therefore,":[58],"during":[59],"inference,":[60,177],"model":[62],"must":[63],"consider":[64],"which":[65],"article-topics":[66,85,175],"were":[67],"theoretically":[68],"used":[69],"generate":[71],"corpus.":[73],"Since":[74],"tend":[78],"quite":[81],"large,":[82],"many":[84],"considered":[86],"slow":[87],"down":[88],"inference":[90],"process.":[91,182],"increase":[93,114,216,223,230,235,242,250],"in":[94,110,217,224,231,236,243,251],"execution":[95,129],"time":[96],"is":[97],"significant,":[98],"with":[99],"source":[101,139,151,211],"input":[102],"greater":[103],"than":[104],"103":[105],"becoming":[106],"unfeasible":[107],"use":[109],"modeling.":[112],"To":[113],"applicability":[116],"models,":[120],"approaches":[121],"are":[122],"needed":[123],"speed":[125],"up":[126,179],"overall":[128,181],"time.":[130],"This":[131],"paper":[132],"presents":[133],"way":[135],"ranking":[137,168,185],"satisfy":[142],"above":[144],"goal.":[145],"Our":[146],"approach":[147,196],"utilizes":[148],"ranking,":[152],"based":[153],"PageRank":[156],"algorithm,":[157],"determine":[159],"importance":[161],"article-topic.":[164],"By":[165],"applying":[166],"our":[167,195,208],"technique":[169,186],"we":[170],"eliminate":[172],"low":[173],"scoring":[174],"before":[176],"speeding":[178],"Remarkably,":[183],"this":[184],"also":[188],"perplexity":[190],"interpretability.":[192],"Results":[193],"show":[194],"outperform":[198],"baseline":[199,256],"methods":[200],"significantly":[202],"aid":[203],"models.":[206],"In":[207],"evaluation,":[209],"rankings":[212],"yield":[213],"44%":[215],"retrieval":[219],"f-score,":[220],"42.6%":[222],"inter-inference":[225],"elimination,":[227],"64%":[229],"perplexity,":[232],"30%":[234],"token":[237],"assignment":[238,253],"accuracy,":[239],"20%":[241],"composition":[245],"interpretability,":[246],"5%":[249],"document":[252],"interpretability":[254],"over":[255],"methods.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}