{"id":"https://openalex.org/W4411928761","doi":"https://doi.org/10.3390/bdcc9070175","title":"Using Vector Databases for the Selection of Related Occupations: An Empirical Evaluation Using O*NET","display_name":"Using Vector Databases for the Selection of Related Occupations: An Empirical Evaluation Using O*NET","publication_year":2025,"publication_date":"2025-07-02","ids":{"openalex":"https://openalex.org/W4411928761","doi":"https://doi.org/10.3390/bdcc9070175"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc9070175","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070175","pdf_url":"https://www.mdpi.com/2504-2289/9/7/175/pdf?version=1751451478","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/9/7/175/pdf?version=1751451478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5098882522","display_name":"Lino Gonzalez-Garcia","orcid":"https://orcid.org/0000-0002-0442-3399"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Lino Gonzalez-Garcia","raw_affiliation_strings":["Computer Science Department, Universidad de Alcal\u00e1, 28801 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universidad de Alcal\u00e1, 28801 Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043345274","display_name":"Miguel\u2010\u00c1ngel Sicilia","orcid":"https://orcid.org/0000-0003-3067-4180"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Miguel-Angel Sicilia","raw_affiliation_strings":["Computer Science Department, Universidad de Alcal\u00e1, 28801 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universidad de Alcal\u00e1, 28801 Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051969166","display_name":"Elena Garc\u00eda\u2010Barriocanal","orcid":"https://orcid.org/0000-0001-6752-9599"},"institutions":[{"id":"https://openalex.org/I189268942","display_name":"Universidad de Alcal\u00e1","ror":"https://ror.org/04pmn0e78","country_code":"ES","type":"education","lineage":["https://openalex.org/I189268942"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Elena Garc\u00eda-Barriocanal","raw_affiliation_strings":["Computer Science Department, Universidad de Alcal\u00e1, 28801 Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Universidad de Alcal\u00e1, 28801 Madrid, Spain","institution_ids":["https://openalex.org/I189268942"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5098882522"],"corresponding_institution_ids":["https://openalex.org/I189268942"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21473788,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"7","first_page":"175","last_page":"175"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12401","display_name":"Scheduling and Timetabling Solutions","score":0.8920000195503235,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12401","display_name":"Scheduling and Timetabling Solutions","score":0.8920000195503235,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13722","display_name":"Ergonomics and Human Factors","score":0.8348000049591064,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10703","display_name":"Business Process Modeling and Analysis","score":0.7828999757766724,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6654472947120667},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.561479926109314},{"id":"https://openalex.org/keywords/net","display_name":"Net (polyhedron)","score":0.5554189682006836},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4814997911453247},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32523107528686523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2656828463077545},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2399897575378418}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6654472947120667},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.561479926109314},{"id":"https://openalex.org/C14166107","wikidata":"https://www.wikidata.org/wiki/Q253829","display_name":"Net (polyhedron)","level":2,"score":0.5554189682006836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4814997911453247},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32523107528686523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2656828463077545},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2399897575378418},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/bdcc9070175","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070175","pdf_url":"https://www.mdpi.com/2504-2289/9/7/175/pdf?version=1751451478","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:13a630c1686f4eb5aa907525af782986","is_oa":true,"landing_page_url":"https://doaj.org/article/13a630c1686f4eb5aa907525af782986","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":"Big Data and Cognitive Computing, Vol 9, Iss 7, p 175 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc9070175","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc9070175","pdf_url":"https://www.mdpi.com/2504-2289/9/7/175/pdf?version=1751451478","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411928761.pdf","grobid_xml":"https://content.openalex.org/works/W4411928761.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1978225408","https://openalex.org/W2049403204","https://openalex.org/W2107590910","https://openalex.org/W2109537183","https://openalex.org/W2286318994","https://openalex.org/W2972358271","https://openalex.org/W3114950584","https://openalex.org/W3134593225","https://openalex.org/W3202227681","https://openalex.org/W4221143046","https://openalex.org/W4292779060","https://openalex.org/W4297154361","https://openalex.org/W4377293882","https://openalex.org/W4380786847","https://openalex.org/W4391849320","https://openalex.org/W4400641571","https://openalex.org/W4400700563","https://openalex.org/W4400910146","https://openalex.org/W4407246036","https://openalex.org/W4408103423","https://openalex.org/W4408854165","https://openalex.org/W6778883912","https://openalex.org/W6809646742","https://openalex.org/W6853729823"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Career":[0],"planning":[1],"agencies":[2],"and":[3,32,40,70,73,104,114,154],"other":[4,177,249],"organizations":[5],"can":[6,48],"help":[7],"workers":[8],"if":[9],"they":[10,47,174],"are":[11,19,160,254],"able":[12],"to":[13,21,37,51,61,123,127],"effectively":[14],"identify":[15],"related":[16,54,63,96,225],"occupations":[17,39,64,179,226,243],"that":[18,46,234,253,270],"relevant":[20,178],"the":[22,89,116,125,133,147,155,164,185,193,230,238,257,261,266],"task":[23],"at":[24],"hand.":[25],"Occupational":[26],"knowledge":[27],"bases":[28],"such":[29],"as":[30,210],"O*NET":[31,117],"ESCO":[33],"represent":[34],"mature":[35],"attempts":[36],"categorize":[38],"describe":[41],"them":[42],"in":[43,136,163,192,202,229,244,263,280],"detail":[44],"so":[45],"be":[49,274],"used":[50],"search":[52],"for":[53,78,95,107,189,200],"occupations.":[55],"Vector":[56],"databases":[57,94],"offer":[58],"an":[59],"opportunity":[60],"find":[62],"based":[65,180],"on":[66,181],"large":[67],"pre-trained":[68],"word":[69],"sentence":[71,152],"embeddings":[72],"their":[74],"associated":[75],"retrieval":[76,98,105,166,206,272],"algorithms":[77],"similarity":[79,236],"search.":[80],"This":[81,268],"paper":[82],"reports":[83],"a":[84,137,213],"systematic":[85],"empirical":[86],"evaluation":[87],"of":[88,91,139,146,157,212,221,241,260,265],"possibilities":[90],"using":[92,99,115],"vector":[93,112,204],"occupation":[97],"different":[100,251],"document":[101],"structures,":[102],"embeddings,":[103,153],"configurations":[106],"two":[108],"popular":[109],"open":[110],"source":[111],"databases,":[113],"curated":[118,129,171,231],"database.":[119],"The":[120,141,219],"objective":[121],"was":[122],"understand":[124],"extent":[126],"which":[128,196,203],"relations":[130,135,279],"capture":[131],"all":[132,161],"meaningful":[134],"context":[138],"retrieval.":[140],"results":[142,194],"show":[143],"that,":[144],"independent":[145],"database":[148,205,232,262],"used,":[149],"distance":[150],"metrics,":[151],"selection":[156],"text":[158,182,235,271],"fragments":[159],"significant":[162],"overall":[165],"performance":[167],"when":[168],"comparing":[169],"with":[170,276],"relations,":[172],"but":[173,247],"also":[175,248],"retrieve":[176],"similarity.":[183],"Further,":[184],"precision":[186],"is":[187,197,207],"high":[188],"smaller":[190],"cutoffs":[191],"list,":[195],"especially":[198],"important":[199],"settings":[201],"set":[208],"up":[209],"part":[211],"Retrieval":[214],"Augmented":[215],"Generation":[216],"(RAG)":[217],"pattern.":[218],"inspection":[220],"highly":[222],"ranked":[223],"retrieved":[224],"not":[227],"explicit":[228,278],"reveals":[233],"captures":[237],"taxonomical":[239],"grouping":[240],"some":[242,245],"cases,":[246],"cross-cuts":[250],"aspects":[252],"distinct":[255],"from":[256],"hierarchical":[258],"organization":[259],"most":[264],"cases.":[267],"suggests":[269],"should":[273],"combined":[275],"querying":[277],"practical":[281],"applications.":[282]},"counts_by_year":[],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}