{"id":"https://openalex.org/W2914937009","doi":"https://doi.org/10.1109/bigdata.2018.8622309","title":"Domain-specific Topic Model for Knowledge Discovery through Conversational Agents in Data Intensive Scientific Communities","display_name":"Domain-specific Topic Model for Knowledge Discovery through Conversational Agents in Data Intensive Scientific Communities","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2914937009","doi":"https://doi.org/10.1109/bigdata.2018.8622309","mag":"2914937009"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","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/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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, USA","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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, USA","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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, USA","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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, USA","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, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, University of Missouri, Columbia, USA","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":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4886","last_page":"4895"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13274","display_name":"Expert finding and Q&A systems","score":0.9994000196456909,"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/T13274","display_name":"Expert finding and Q&A systems","score":0.9994000196456909,"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":0.9991999864578247,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9937999844551086,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8027960062026978},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.6609237790107727},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6543226838111877},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6191214323043823},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.6111843585968018},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.5682838559150696},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.49693563580513},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.479384183883667},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44001781940460205},{"id":"https://openalex.org/keywords/perplexity","display_name":"Perplexity","score":0.4212139844894409},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3974328935146332},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.360024631023407},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3289175033569336},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.18598517775535583}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027960062026978},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.6609237790107727},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6543226838111877},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6191214323043823},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6111843585968018},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.5682838559150696},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.49693563580513},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.479384183883667},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44001781940460205},{"id":"https://openalex.org/C100279451","wikidata":"https://www.wikidata.org/wiki/Q372193","display_name":"Perplexity","level":3,"score":0.4212139844894409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3974328935146332},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.360024631023407},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3289175033569336},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.18598517775535583},{"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/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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata.2018.8622309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W602834913","https://openalex.org/W1880262756","https://openalex.org/W1990978509","https://openalex.org/W2001082470","https://openalex.org/W2064354742","https://openalex.org/W2072644219","https://openalex.org/W2107034620","https://openalex.org/W2112050062","https://openalex.org/W2127201730","https://openalex.org/W2129666400","https://openalex.org/W2135790056","https://openalex.org/W2140124448","https://openalex.org/W2140886546","https://openalex.org/W2165599843","https://openalex.org/W2166001595","https://openalex.org/W2171353991","https://openalex.org/W2529193383","https://openalex.org/W4214775604","https://openalex.org/W6639619044","https://openalex.org/W6650793866","https://openalex.org/W6676519436","https://openalex.org/W6681041898","https://openalex.org/W6684489972"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2761847515","https://openalex.org/W130869231","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W4293734197","https://openalex.org/W4206967254","https://openalex.org/W2131689821"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"techniques":[2],"underlying":[3],"Big":[4],"Data":[5],"analytics":[6],"have":[7],"the":[8,67,144,170],"potential":[9],"to":[10,42,69,106,128,132,142,150,184,200],"benefit":[11],"data":[12,130,155,204],"intensive":[13,156],"communities":[14,28],"in":[15,25,66,192],"e.g.,":[16],"bioinformatics":[17,206],"and":[18,36,117,154,176,207,222],"neuroscience":[19,208],"domain":[20,27,62,140,191,242],"sciences.":[21],"Today's":[22],"innovative":[23],"advances":[24],"these":[26],"are":[29],"increasingly":[30],"built":[31],"upon":[32],"multi-disciplinary":[33],"knowledge":[34,43,109],"discovery":[35,44],"cross-domain":[37],"collaborations.":[38],"Consequently,":[39],"shortened":[40],"time":[41],"is":[45,127,163],"a":[46,61,83,93,137,152,164,178,189,228,241],"challenge":[47,59],"when":[48],"investigating":[49],"new":[50,53],"methods,":[51],"developing":[52],"tools,":[54],"or":[55,147],"integrating":[56],"datasets.":[57,223],"The":[58,123],"for":[60,104,139,243],"scientist":[63],"particularly":[64],"lies":[65],"actions":[68],"obtain":[70,133],"guidance":[71,135],"through":[72],"query":[73],"of":[74,82,86,125,203,213,220],"massive":[75],"information":[76],"from":[77,119,205,215],"diverse":[78],"text":[79],"corpus":[80],"comprising":[81],"wide-ranging":[84],"set":[85],"topics.":[87,248],"In":[88],"this":[89],"paper,":[90],"we":[91,231],"propose":[92],"novel":[94],"\"domain-specific":[95],"topic":[96],"model\"":[97],"(DSTM)":[98],"that":[99,168,210,233],"can":[100],"drive":[101],"conversational":[102],"agents":[103],"users":[105],"discover":[107],"latent":[108,186,247],"patterns":[110,187],"about":[111],"relationships":[112],"among":[113],"research":[114,157],"topics,":[115],"tools":[116,146,221],"datasets":[118,148],"exemplar":[120],"scientific":[121],"domains.":[122],"goal":[124],"DSTM":[126,162,199],"perform":[129],"mining":[131],"meaningful":[134],"via":[136],"chatbot":[138],"scientists":[141],"choose":[143],"relevant":[145],"pertinent":[149],"solving":[151],"computational":[153],"problem":[158],"at":[159],"hand.":[160],"Our":[161],"Bayesian":[165],"hierarchical":[166],"model":[167,175,235],"extends":[169],"Latent":[171],"Dirichlet":[172],"Allocation":[173],"(LDA)":[174],"uses":[177],"Markov":[179],"chain":[180],"Monte":[181],"Carlo":[182],"algorithm":[183],"infer":[185],"within":[188,240],"specific":[190,246],"an":[193],"unsupervised":[194],"manner.":[195],"We":[196],"apply":[197],"our":[198,234],"large":[201],"collections":[202],"domains":[209],"include":[211],"hundreds":[212,219],"papers":[214],"reputed":[216],"journal":[217],"archives,":[218],"Through":[224],"evaluation":[225],"experiments":[226],"with":[227],"perplexity":[229],"metric,":[230],"show":[232],"has":[236],"better":[237],"generalization":[238],"performance":[239],"discovering":[244],"highly":[245]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}