{"id":"https://openalex.org/W4416105437","doi":"https://doi.org/10.5220/0013458500003967","title":"Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging","display_name":"Exploring LLM Capabilities in Extracting DCAT-Compatible Metadata for Data Cataloging","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416105437","doi":"https://doi.org/10.5220/0013458500003967"},"language":"en","primary_location":{"id":"doi:10.5220/0013458500003967","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0013458500003967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.05282","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080058484","display_name":"L.S. Busch","orcid":"https://orcid.org/0000-0002-8184-4939"},"institutions":[{"id":"https://openalex.org/I4210148941","display_name":"IU International University of Applied Sciences","ror":"https://ror.org/04fdat027","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210148941"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lennart Busch","raw_affiliation_strings":["IU International University of Applied Sciences, Erfurt, 99084, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IU International University of Applied Sciences, Erfurt, 99084, Germany","institution_ids":["https://openalex.org/I4210148941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067380879","display_name":"Daniel Tebernum","orcid":null},"institutions":[{"id":"https://openalex.org/I4210163630","display_name":"Fraunhofer Institute for Software and Systems Engineering","ror":"https://ror.org/058kjq542","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210163630","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Tebernum","raw_affiliation_strings":["Fraunhofer Institute for Software and Systems Engineering ISST, Dortmund, 44147, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fraunhofer Institute for Software and Systems Engineering ISST, Dortmund, 44147, Germany","institution_ids":["https://openalex.org/I4210163630"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069921146","display_name":"Gissel Velarde","orcid":"https://orcid.org/0000-0001-5392-9540"},"institutions":[{"id":"https://openalex.org/I4210148941","display_name":"IU International University of Applied Sciences","ror":"https://ror.org/04fdat027","country_code":"DE","type":"education","lineage":["https://openalex.org/I4210148941"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gissel Velarde","raw_affiliation_strings":["IU International University of Applied Sciences, Erfurt, 99084, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IU International University of Applied Sciences, Erfurt, 99084, Germany","institution_ids":["https://openalex.org/I4210148941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"299","last_page":"309"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.2728999853134155,"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/T11719","display_name":"Data Quality and Management","score":0.2728999853134155,"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/T11937","display_name":"Research Data Management Practices","score":0.09459999948740005,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.0763000026345253,"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/metadata","display_name":"Metadata","score":0.9531999826431274},{"id":"https://openalex.org/keywords/data-element","display_name":"Data element","score":0.6553000211715698},{"id":"https://openalex.org/keywords/metadata-repository","display_name":"Metadata repository","score":0.564300000667572},{"id":"https://openalex.org/keywords/cataloging","display_name":"Cataloging","score":0.48840001225471497},{"id":"https://openalex.org/keywords/metadata-management","display_name":"Metadata management","score":0.43369999527931213},{"id":"https://openalex.org/keywords/meta-data-services","display_name":"Meta Data Services","score":0.3747999966144562},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.3675999939441681},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.3587000072002411}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9531999826431274},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627000212669373},{"id":"https://openalex.org/C30872290","wikidata":"https://www.wikidata.org/wiki/Q1172389","display_name":"Data element","level":3,"score":0.6553000211715698},{"id":"https://openalex.org/C153048206","wikidata":"https://www.wikidata.org/wiki/Q3454922","display_name":"Metadata repository","level":3,"score":0.564300000667572},{"id":"https://openalex.org/C2777922441","wikidata":"https://www.wikidata.org/wiki/Q3535655","display_name":"Cataloging","level":2,"score":0.48840001225471497},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46000000834465027},{"id":"https://openalex.org/C2779489174","wikidata":"https://www.wikidata.org/wiki/Q6822246","display_name":"Metadata management","level":3,"score":0.43369999527931213},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4296000003814697},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C136976847","wikidata":"https://www.wikidata.org/wiki/Q6822297","display_name":"Meta Data Services","level":4,"score":0.3747999966144562},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3587000072002411},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3386000096797943},{"id":"https://openalex.org/C158746014","wikidata":"https://www.wikidata.org/wiki/Q17085509","display_name":"Data management plan","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C69075417","wikidata":"https://www.wikidata.org/wiki/Q515701","display_name":"Linked data","level":3,"score":0.31690001487731934},{"id":"https://openalex.org/C137314826","wikidata":"https://www.wikidata.org/wiki/Q2330408","display_name":"Data mapping","level":2,"score":0.31470000743865967},{"id":"https://openalex.org/C110326360","wikidata":"https://www.wikidata.org/wiki/Q17149476","display_name":"Metadata modeling","level":4,"score":0.28529998660087585},{"id":"https://openalex.org/C100463513","wikidata":"https://www.wikidata.org/wiki/Q5227322","display_name":"Data model (GIS)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C193150823","wikidata":"https://www.wikidata.org/wiki/Q1477538","display_name":"Geospatial metadata","level":5,"score":0.28200000524520874},{"id":"https://openalex.org/C103692084","wikidata":"https://www.wikidata.org/wiki/Q1765824","display_name":"Semantic grid","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25600001215934753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5220/0013458500003967","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0013458500003967","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th International Conference on Data Science, Technology and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.05282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05282","pdf_url":"https://arxiv.org/pdf/2507.05282","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.05282","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.05282","pdf_url":"https://arxiv.org/pdf/2507.05282","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Efficient":[0],"data":[1,6,32,49,86],"exploration":[2,50],"is":[3,64,70],"crucial":[4],"as":[5,59,108],"becomes":[7],"increasingly":[8],"important":[9],"for":[10,30,104,117],"accelerating":[11],"processes,":[12],"improving":[13],"forecasts":[14],"and":[15,39,47,62,72,87,95,110,144,164,179],"developing":[16],"new":[17],"business":[18],"models.":[19],"Data":[20,43],"consumers":[21],"often":[22,65],"spend":[23],"25-98":[24],"%":[25],"of":[26,41,84,176],"their":[27],"time":[28],"searching":[29],"suitable":[31],"due":[33],"to":[34,54,128,167],"the":[35],"exponential":[36],"growth,":[37],"heterogeneity":[38],"distribution":[40],"data.":[42],"catalogs":[44],"can":[45,80,124],"support":[46],"accelerate":[48],"by":[51],"using":[52],"metadata":[53,60,82,106,126],"answer":[55],"user":[56],"queries.":[57],"However,":[58],"creation":[61],"maintenance":[63,83],"a":[66,114,162,170],"manual":[67],"process,":[68],"it":[69],"time-consuming":[71],"requires":[73,173],"expertise.":[74],"This":[75],"study":[76],"investigates":[77],"whether":[78],"LLMs":[79,100,123,160],"automate":[81],"text-based":[85],"generate":[88,125],"high-quality":[89],"DCAT-compatible":[90],"metadata.":[91],"We":[92],"tested":[93],"zero-shot":[94],"few-shot":[96,151],"prompting":[97,152],"strategies":[98],"with":[99,113],"from":[101],"different":[102],"vendors":[103],"generating":[105],"such":[107],"titles":[109],"keywords,":[111],"along":[112],"fine-tuned":[115],"model":[116],"classification.":[118],"Our":[119],"results":[120,155],"show":[121],"that":[122,134],"comparable":[127],"human-created":[129],"content,":[130],"particularly":[131],"on":[132],"tasks":[133],"require":[135],"advanced":[136],"semantic":[137],"understanding.":[138],"Larger":[139],"models":[140],"outperformed":[141],"smaller":[142],"ones,":[143],"fine-tuning":[145],"significantly":[146],"improves":[147],"classification":[148],"accuracy,":[149],"while":[150],"yields":[153],"better":[154],"in":[156],"most":[157],"cases.":[158],"Although":[159],"offer":[161],"faster":[163],"reliable":[165],"way":[166],"create":[168],"metadata,":[169],"successful":[171],"application":[172],"careful":[174],"consideration":[175],"task-specific":[177],"criteria":[178],"domain":[180],"context.":[181]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}