{"id":"https://openalex.org/W4236389726","doi":"https://doi.org/10.1109/tkde.2021.3093350","title":"Domain-specific Topic Model for Knowledge Discovery in Computational and Data-Intensive Scientific Communities","display_name":"Domain-specific Topic Model for Knowledge Discovery in Computational and Data-Intensive Scientific Communities","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W4236389726","doi":"https://doi.org/10.1109/tkde.2021.3093350","pmid":"https://pubmed.ncbi.nlm.nih.gov/36798878"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2021.3093350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3093350","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9928187","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108029747","display_name":"Yuanxun Zhang","orcid":"https://orcid.org/0000-0002-7970-6086"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuanxun Zhang","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072008189","display_name":"Prasad Calyam","orcid":"https://orcid.org/0000-0002-7666-5389"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasad Calyam","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071079252","display_name":"Trupti Joshi","orcid":"https://orcid.org/0000-0001-8944-4924"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Trupti Joshi","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036797460","display_name":"Satish S. Nair","orcid":"https://orcid.org/0000-0002-1489-7029"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Satish Nair","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082428303","display_name":"Dong Xu","orcid":"https://orcid.org/0000-0002-4809-0514"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Xu","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri-Columbia, Columbia, MO, 65211","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":1.0919,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.82231989,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"35","issue":"2","first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T13910","display_name":"Computational and Text Analysis Methods","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9839000105857849,"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/computer-science","display_name":"Computer science","score":0.8228752613067627},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6501710414886475},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5919497013092041},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.581323504447937},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5671826601028442},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.5339096188545227},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.504637598991394},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.49980854988098145},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4639859199523926},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4330441951751709},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4262411296367645},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.418911874294281},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.40147215127944946},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33920061588287354},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3225712180137634},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.1514805257320404}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8228752613067627},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6501710414886475},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5919497013092041},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.581323504447937},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5671826601028442},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.5339096188545227},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.504637598991394},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.49980854988098145},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4639859199523926},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4330441951751709},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262411296367645},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.418911874294281},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40147215127944946},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33920061588287354},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3225712180137634},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.1514805257320404},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tkde.2021.3093350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2021.3093350","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},{"id":"pmid:36798878","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36798878","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on knowledge and data engineering","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9928187","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9928187","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Knowl Data Eng","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:pubmedcentral.nih.gov:9928187","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9928187","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Trans Knowl Data Eng","raw_type":"Text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G222960579","display_name":null,"funder_award_id":"R01 MH122023","funder_id":"https://openalex.org/F4320337346","funder_display_name":"National Institute of Mental Health"}],"funders":[{"id":"https://openalex.org/F4320337346","display_name":"National Institute of Mental Health","ror":"https://ror.org/04xeg9z08"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W665341","https://openalex.org/W163868085","https://openalex.org/W1587835186","https://openalex.org/W1638753340","https://openalex.org/W1892382968","https://openalex.org/W1959608418","https://openalex.org/W1977676276","https://openalex.org/W1987971958","https://openalex.org/W1990978509","https://openalex.org/W2001082470","https://openalex.org/W2007339694","https://openalex.org/W2038043464","https://openalex.org/W2060300932","https://openalex.org/W2064354742","https://openalex.org/W2072644219","https://openalex.org/W2080046063","https://openalex.org/W2085487226","https://openalex.org/W2089570507","https://openalex.org/W2103441770","https://openalex.org/W2107034620","https://openalex.org/W2108234281","https://openalex.org/W2124985265","https://openalex.org/W2127201730","https://openalex.org/W2129666400","https://openalex.org/W2135194391","https://openalex.org/W2135790056","https://openalex.org/W2140886546","https://openalex.org/W2147152072","https://openalex.org/W2155893237","https://openalex.org/W2160170318","https://openalex.org/W2166001595","https://openalex.org/W2171353991","https://openalex.org/W2225156818","https://openalex.org/W2405248387","https://openalex.org/W2529193383","https://openalex.org/W2757016771","https://openalex.org/W2770468636","https://openalex.org/W2808787330","https://openalex.org/W2808830345","https://openalex.org/W2909337318","https://openalex.org/W2914937009","https://openalex.org/W2952478253","https://openalex.org/W2953062473","https://openalex.org/W2963348221","https://openalex.org/W2963707260","https://openalex.org/W4214775604","https://openalex.org/W4233135949","https://openalex.org/W4237791300","https://openalex.org/W4247445178","https://openalex.org/W4252060112","https://openalex.org/W6636440780","https://openalex.org/W6640963894","https://openalex.org/W6676519436","https://openalex.org/W6680343917","https://openalex.org/W6684489972","https://openalex.org/W6685356407","https://openalex.org/W6688325169","https://openalex.org/W6734688555","https://openalex.org/W6920924752"],"related_works":["https://openalex.org/W2761847515","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W4293734197","https://openalex.org/W2207653751","https://openalex.org/W4206967254","https://openalex.org/W2131689821"],"abstract_inverted_index":{"Shortened":[0],"time":[1],"to":[2,34,74,114,130,203],"knowledge":[3,9,77,209],"discovery":[4],"and":[5,15,22,85,105,137,156,170,207],"adapting":[6],"prior":[7],"domain":[8,28,121],"is":[10,93],"a":[11,27,48,68,94,119,192],"challenge":[12,25],"for":[13,26,186],"computational":[14],"data-intensive":[16],"communities":[17],"such":[18],"as":[19],"e.g.,":[20],"bioinformatics":[21,136],"neuroscience.":[23],"The":[24],"scientist":[29],"lies":[30],"in":[31,122,162],"the":[32,99,107,148,182],"actions":[33],"obtain":[35],"guidance":[36],"through":[37],"query":[38],"of":[39,47,51,133,145,154],"massive":[40],"information":[41,171],"from":[42,87,135,200],"diverse":[43],"text":[44],"corpus":[45],"comprising":[46],"wide-ranging":[49],"set":[50],"topics":[52,190],"when:":[53],"investigating":[54],"new":[55,58],"methods,":[56],"developing":[57],"tools,":[59],"or":[60],"integrating":[61],"datasets.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,195],"propose":[67],"novel":[69],"\"domain-specific":[70],"topic":[71],"model\"":[72],"(DSTM)":[73],"discover":[75,204],"latent":[76,116,189],"patterns":[78,117],"about":[79],"relationships":[80],"among":[81],"research":[82],"topics,":[83],"tools":[84,155],"datasets":[86,157],"exemplary":[88],"scientific":[89],"domains.":[90],"Our":[91],"DSTM":[92,129,202],"generative":[95],"model":[96,104,177],"that":[97,140,158,175,198],"extends":[98],"Latent":[100],"Dirichlet":[101],"Allocation":[102],"(LDA)":[103],"uses":[106],"Markov":[108],"chain":[109],"Monte":[110],"Carlo":[111],"(MCMC)":[112],"algorithm":[113],"infer":[115],"within":[118,191],"specific":[120],"an":[123],"unsupervised":[124],"manner.":[125],"We":[126],"apply":[127],"our":[128,176,201],"large":[131],"collections":[132],"data":[134],"neuroscience":[138],"domains":[139],"include":[141],"more":[142],"than":[143,181],"25,000":[144],"papers":[146],"over":[147],"last":[149],"ten":[150],"years,":[151],"featuring":[152],"hundreds":[153],"are":[159],"commonly":[160],"used":[161],"relevant":[163],"studies.":[164],"Evaluation":[165],"experiments":[166],"based":[167],"on":[168],"generalization":[169],"retrieval":[172],"metrics":[173],"show":[174],"has":[178],"better":[179],"performance":[180],"state-of-the-art":[183],"baseline":[184],"models":[185],"discovering":[187],"highly-specific":[188],"domain.":[193],"Lastly,":[194],"demonstrate":[196],"applications":[197],"benefit":[199],"intra-domain,":[205],"cross-domain":[206],"trend":[208],"patterns.":[210]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}