{"id":"https://openalex.org/W4402673792","doi":"https://doi.org/10.1109/e-science62913.2024.10678676","title":"Discovering Research Areas in Dataset Applications through Knowledge Graphs and Large Language Models","display_name":"Discovering Research Areas in Dataset Applications through Knowledge Graphs and Large Language Models","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4402673792","doi":"https://doi.org/10.1109/e-science62913.2024.10678676"},"language":"en","primary_location":{"id":"doi:10.1109/e-science62913.2024.10678676","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/e-science62913.2024.10678676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"},"type":"article","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/A5048651333","display_name":"Irina Gerasimov","orcid":"https://orcid.org/0000-0003-0224-5004"},"institutions":[{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Irina Gerasimov","raw_affiliation_strings":["ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA"],"affiliations":[{"raw_affiliation_string":"ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA","institution_ids":["https://openalex.org/I1306266525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014196859","display_name":"Armin Mehrabian","orcid":"https://orcid.org/0000-0003-0587-9387"},"institutions":[{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Armin Mehrabian","raw_affiliation_strings":["ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA"],"affiliations":[{"raw_affiliation_string":"ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA","institution_ids":["https://openalex.org/I1306266525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008704156","display_name":"Binita Kc","orcid":"https://orcid.org/0000-0001-6126-5369"},"institutions":[{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Binita KC","raw_affiliation_strings":["ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA"],"affiliations":[{"raw_affiliation_string":"ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA","institution_ids":["https://openalex.org/I1306266525"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002350708","display_name":"Jerome Alfred","orcid":"https://orcid.org/0000-0002-1203-7113"},"institutions":[{"id":"https://openalex.org/I1306266525","display_name":"Goddard Space Flight Center","ror":"https://ror.org/0171mag52","country_code":"US","type":"facility","lineage":["https://openalex.org/I1306266525","https://openalex.org/I4210124779"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jerome Alfred","raw_affiliation_strings":["ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA"],"affiliations":[{"raw_affiliation_string":"ADNET Systems, Inc,NASA Goddard Space Flight Center,Greenbelt,MD,USA","institution_ids":["https://openalex.org/I1306266525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007920767","display_name":"Michael P. McGuire","orcid":"https://orcid.org/0000-0001-7585-8018"},"institutions":[{"id":"https://openalex.org/I4322298","display_name":"Towson University","ror":"https://ror.org/044w7a341","country_code":"US","type":"education","lineage":["https://openalex.org/I4322298"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael P. McGuire","raw_affiliation_strings":["Towson University,Department of Computer and Information Sciences,Towson,MD,USA"],"affiliations":[{"raw_affiliation_string":"Towson University,Department of Computer and Information Sciences,Towson,MD,USA","institution_ids":["https://openalex.org/I4322298"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5048651333"],"corresponding_institution_ids":["https://openalex.org/I1306266525"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13408282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.9581999778747559,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.9581999778747559,"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/T10028","display_name":"Topic Modeling","score":0.9333000183105469,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9178000092506409,"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":0.7266198396682739},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.6146571636199951},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.48701030015945435},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4115133583545685},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36480629444122314},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32365643978118896}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7266198396682739},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.6146571636199951},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.48701030015945435},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4115133583545685},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36480629444122314},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32365643978118896}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/e-science62913.2024.10678676","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/e-science62913.2024.10678676","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 20th International Conference on e-Science (e-Science)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.44999998807907104,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2003012803","https://openalex.org/W2755996600","https://openalex.org/W2810791964","https://openalex.org/W2926805670","https://openalex.org/W2970771982","https://openalex.org/W2991202624","https://openalex.org/W3122659278","https://openalex.org/W3159316741","https://openalex.org/W4224282622","https://openalex.org/W4390692489","https://openalex.org/W4390829472","https://openalex.org/W4400136007","https://openalex.org/W4404783735","https://openalex.org/W6755207826","https://openalex.org/W6948699253"],"related_works":["https://openalex.org/W3188962172","https://openalex.org/W2772917594","https://openalex.org/W4306742369","https://openalex.org/W4303457083","https://openalex.org/W2131146434","https://openalex.org/W2951359407","https://openalex.org/W4376623224","https://openalex.org/W3136979370","https://openalex.org/W4387849428","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Scientific":[0],"datasets":[1,26,55,67,197,235],"are":[2,27,68],"increasingly":[3],"cited":[4,130],"in":[5,36,131,145,252],"peer-reviewed":[6],"journal":[7],"publications,":[8],"facilitating":[9],"easy":[10],"access":[11],"to":[12,34,79,95,111,126,198,225],"research":[13,148,183,193,200],"utilizing":[14],"those":[15],"datasets.":[16],"Datasets":[17],"undergo":[18],"a":[19,49,71,92,119,162,212,226],"life":[20,101,137],"cycle":[21,102,138],"where":[22],"older":[23],"versions":[24,31,115],"of":[25,65,83,103,164,173,180,216,258],"replaced":[28],"by":[29],"newer":[30,63],"often":[32],"due":[33],"improvements":[35],"data":[37,239,262],"resolution,":[38],"algorithms,":[39],"and":[40,61,116,139,205,228,231,244,250],"other":[41],"factors.":[42],"Unlike":[43],"peer":[44],"reviewed":[45],"documents":[46],"registered":[47,69],"with":[48,70],"single":[50],"Digital":[51],"Unique":[52],"Identifier":[53],"(DOI),":[54],"can":[56,124],"be":[57,96],"updated":[58],"over":[59,98,133],"time":[60],"the":[62,66,80,84,99,113,128,134,152,174,186,203,237],"version":[64,82],"new":[72],"DOI":[73],"which":[74],"is":[75,87,247],"not":[76],"necessarily":[77],"linked":[78],"previous":[81],"dataset.":[85,105],"It":[86],"challenging":[88],"when":[89],"publications":[90,117,132,166,175],"citing":[91],"dataset":[93,114,129,136,143,253],"need":[94],"traced":[97],"entire":[100,135],"that":[104,171],"We":[106,150],"provide":[107],"an":[108],"innovative":[109],"approach":[110,246],"link":[112],"using":[118],"knowledge":[120],"graph":[121],"(KG).":[122],"KG":[123,204,243],"help":[125],"trace":[127],"shed":[140],"light":[141],"into":[142,178,191],"usage":[144],"various":[146],"applied":[147,182,199],"areas.":[149,194],"fine-tuned":[151],"pretrained":[153],"NASA":[154],"IMPACT":[155],"INDUS":[156],"Large":[157],"Language":[158],"Model":[159],"(LLM)":[160],"on":[161],"set":[163],"labeled":[165],"abstracts.":[167],"Our":[168],"results":[169],"showed":[170],"87%":[172],"were":[176,189],"classified":[177,190],"one":[179,257],"twenty":[181],"areas,":[184],"while":[185],"remaining":[187],"13%":[188],"non-applied":[192],"By":[195],"linking":[196],"areas":[201],"through":[202],"employing":[206],"Global":[207],"Change":[208],"Master":[209],"Directory":[210],"(GCMD),":[211],"well-established":[213],"controlled":[214],"vocabulary":[215],"scientific":[217],"keywords":[218],"describing":[219],"Earth":[220,238,260],"science":[221,261],"datasets,":[222],"we":[223],"contribute":[224],"transparent":[227],"advanced":[229],"search":[230],"discovery":[232],"mechanism":[233],"for":[234],"across":[236],"ecosystem.":[240],"The":[241],"integrated":[242],"LLM":[245],"now":[248],"incorporated":[249],"operational":[251],"publication":[254],"management":[255],"at":[256],"NASA\u2019s":[259],"archival":[263],"centers.":[264]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}