{"id":"https://openalex.org/W4404294861","doi":"https://doi.org/10.1109/idsta62194.2024.10746941","title":"TAGIFY: LLM-powered Tagging Interface for Improved Data Findability on OGD portals","display_name":"TAGIFY: LLM-powered Tagging Interface for Improved Data Findability on OGD portals","publication_year":2024,"publication_date":"2024-09-24","ids":{"openalex":"https://openalex.org/W4404294861","doi":"https://doi.org/10.1109/idsta62194.2024.10746941"},"language":"en","primary_location":{"id":"doi:10.1109/idsta62194.2024.10746941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/idsta62194.2024.10746941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Fifth International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","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/A5107590684","display_name":"Kevin Kliimask","orcid":null},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":true,"raw_author_name":"Kevin Kliimask","raw_affiliation_strings":["Institute of Computer Science, University of Tartu,Tartu,Estonia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Tartu,Tartu,Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086523033","display_name":"Anastasija Nikiforova","orcid":"https://orcid.org/0000-0002-0532-3488"},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Anastasija Nikiforova","raw_affiliation_strings":["Institute of Computer Science, University of Tartu,Faculty of Science and Technology,Tartu,Estonia"],"affiliations":[{"raw_affiliation_string":"Institute of Computer Science, University of Tartu,Faculty of Science and Technology,Tartu,Estonia","institution_ids":["https://openalex.org/I56085075"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107590684"],"corresponding_institution_ids":["https://openalex.org/I56085075"],"apc_list":null,"apc_paid":null,"fwci":1.6879,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87105176,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"18","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9301000237464905,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9301000237464905,"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/T11719","display_name":"Data Quality and Management","score":0.9023000001907349,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7309188842773438},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5270652770996094},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5203732848167419},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4124471843242645},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07232585549354553}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7309188842773438},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5270652770996094},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5203732848167419},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4124471843242645},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07232585549354553},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/idsta62194.2024.10746941","is_oa":false,"landing_page_url":"https://doi.org/10.1109/idsta62194.2024.10746941","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 Fifth International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","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":22,"referenced_works":["https://openalex.org/W2128802881","https://openalex.org/W2158792003","https://openalex.org/W2302501749","https://openalex.org/W2345455629","https://openalex.org/W2537262135","https://openalex.org/W2548906251","https://openalex.org/W2941195982","https://openalex.org/W2979694655","https://openalex.org/W2983408043","https://openalex.org/W3007730511","https://openalex.org/W3016458989","https://openalex.org/W3095464614","https://openalex.org/W3118934842","https://openalex.org/W4293801884","https://openalex.org/W4386483579","https://openalex.org/W4391600440","https://openalex.org/W4392971742","https://openalex.org/W4396814711","https://openalex.org/W4399255163","https://openalex.org/W6784771137","https://openalex.org/W6867303513","https://openalex.org/W6929796169"],"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":{"Efforts":[0],"directed":[1],"towards":[2],"promoting":[3],"Open":[4,66,102],"Government":[5],"Data":[6,67,103],"(OGD)":[7],"have":[8,73],"gained":[9],"significant":[10],"traction":[11],"across":[12],"various":[13],"governmental":[14],"tiers":[15],"since":[16],"the":[17,64,95,100],"mid-2000s.":[18],"As":[19],"more":[20],"datasets":[21,52,72,122,158],"are":[22],"published":[23],"on":[24,63,127,174],"OGD":[25,128,175],"portals,":[26],"finding":[27],"specific":[28],"data":[29,90,125,168,172,178],"becomes":[30],"harder,":[31],"leading":[32],"to":[33,55,84,99,115,120,123,151,192],"information":[34],"overload":[35],"and":[36,41,59,92,149,161,170,187],"so-called":[37],"\u201cdark":[38],"data\u201d.":[39],"Complete":[40],"accurate":[42],"documentation":[43],"of":[44,48,111,137],"datasets,":[45],"including":[46],"association":[47],"proper":[49],"tags":[50,156],"with":[51],"is":[53,106,114],"key":[54],"improving":[56,171],"dataset":[57,153],"findability":[58,91,126,173],"accessibility.":[60],"Analysis":[61],"conducted":[62],"Estonian":[65],"Portal":[68],"revealed":[69],"that":[70,140],"11%":[71],"no":[74],"associated":[75],"tags,":[76],"while":[77],"26%":[78],"had":[79],"only":[80],"one":[81],"tag":[82],"assigned":[83],"them,":[85],"which":[86],"underscores":[87],"challenges":[88],"in":[89,159],"accessibility":[93],"within":[94],"portal,":[96],"which,":[97],"according":[98],"recent":[101],"Maturity":[104],"Report,":[105],"considered":[107],"trendsetter.":[108],"The":[109,180],"aim":[110],"this":[112],"study":[113],"propose":[116],"an":[117,194],"automated":[118],"solution":[119,182],"tagging":[121,138],"improve":[124],"portals.":[129],"This":[130],"paper":[131],"presents":[132],"TAGIFY":[133],"\u2013":[134],"a":[135],"prototype":[136,198],"interface":[139],"employs":[141],"large":[142],"language":[143],"models":[144],"(LLM)":[145],"such":[146],"as":[147],"GPT-3.5turbo":[148],"GPT-4":[150],"automate":[152],"tagging,":[154],"generating":[155],"for":[157,196],"English":[160],"Estonian,":[162],"thereby":[163],"augmenting":[164],"metadata":[165],"preparation":[166],"by":[167,177,185],"publishers":[169],"portals":[176],"users.":[179],"developed":[181],"was":[183,190],"evaluated":[184],"users":[186],"their":[188],"feedback":[189],"collected":[191],"define":[193],"agenda":[195],"future":[197],"improvements.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}
