{"id":"https://openalex.org/W4410357010","doi":"https://doi.org/10.1145/3672608.3707718","title":"JobSet: Synthetic Job Advertisements Dataset for Labour Market Intelligence","display_name":"JobSet: Synthetic Job Advertisements Dataset for Labour Market Intelligence","publication_year":2025,"publication_date":"2025-03-31","ids":{"openalex":"https://openalex.org/W4410357010","doi":"https://doi.org/10.1145/3672608.3707718"},"language":"en","primary_location":{"id":"doi:10.1145/3672608.3707718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707718","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707718","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707718","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117539811","display_name":"Samuele Colombo","orcid":"https://orcid.org/0009-0001-4958-927X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Samuele Colombo","raw_affiliation_strings":["University of Milano-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102781905","display_name":"Simone D\u2019Amico","orcid":"https://orcid.org/0009-0002-2820-0277"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Simone D'Amico","raw_affiliation_strings":["Department of Economics, Management and Statistics, University of Milano-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Economics, Management and Statistics, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046882068","display_name":"Lorenzo Malandri","orcid":"https://orcid.org/0000-0002-0222-9365"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Lorenzo Malandri","raw_affiliation_strings":["Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047827615","display_name":"Fabio Mercorio","orcid":"https://orcid.org/0000-0001-6864-2702"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabio Mercorio","raw_affiliation_strings":["Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036819374","display_name":"Andrea Seveso","orcid":"https://orcid.org/0000-0001-7132-7703"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Andrea Seveso","raw_affiliation_strings":["Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Quantitative Methods, University of Milano-Bicocca, Milan, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5117539811"],"corresponding_institution_ids":["https://openalex.org/I66752286"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14231031,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"928","last_page":"935"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.9890000224113464,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9890000224113464,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.984000027179718,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9810000061988831,"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/computer-science","display_name":"Computer science","score":0.5652694702148438},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.387090802192688},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.37273550033569336},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36747419834136963}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5652694702148438},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.387090802192688},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.37273550033569336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36747419834136963}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3672608.3707718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707718","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707718","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/555062","is_oa":false,"landing_page_url":"https://hdl.handle.net/10281/555062","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.1145/3672608.3707718","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3672608.3707718","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3672608.3707718","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 40th ACM/SIGAPP Symposium on Applied Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5204166843","display_name":null,"funder_award_id":"101004703","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"}],"funders":[{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410357010.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W2947199057","https://openalex.org/W2967171959","https://openalex.org/W3037383500","https://openalex.org/W3086525109","https://openalex.org/W3092288641","https://openalex.org/W3117329469","https://openalex.org/W3117375542","https://openalex.org/W3187033898","https://openalex.org/W4225106321","https://openalex.org/W4281679115","https://openalex.org/W4288102879","https://openalex.org/W4309674289","https://openalex.org/W4385570982","https://openalex.org/W4386576685","https://openalex.org/W4387819628","https://openalex.org/W4390569880","https://openalex.org/W4390692489","https://openalex.org/W6945393950"],"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":{"The":[0,111,183],"use":[1,151],"of":[2,19,51,92,113,118],"online":[3,121],"services":[4],"for":[5,63,191],"advertising":[6],"job":[7,80,99,165,197],"positions":[8],"has":[9],"grown":[10],"in":[11,29,78,130,179],"the":[12,17,26,49,54,90,119,160,204],"last":[13],"decade,":[14],"thanks":[15],"to":[16,24,86,97,146,163,203],"ability":[18],"Online":[20],"Job":[21],"Advertisements":[22],"(OJAs)":[23],"observe":[25],"labour":[27],"market":[28,166],"near":[30],"real-time,":[31],"predict":[32],"new":[33],"occupation":[34],"trends,":[35],"identify":[36],"relevant":[37],"skills,":[38],"and":[39,42,82,106,123,159,173,196,199],"support":[40],"policy":[41],"decision-making":[43],"activities.":[44],"Unsurprisingly,":[45],"2023":[46],"was":[47],"declared":[48],"Year":[50],"Skills":[52],"by":[53],"EU,":[55],"as":[56],"skill":[57,131,194],"mismatch":[58],"is":[59,126,200],"a":[60,68,75,188],"key":[61,76],"challenge":[62],"European":[64],"economies.":[65],"In":[66],"such":[67],"scenario,":[69],"machine":[70],"learning-based":[71],"approaches":[72],"have":[73],"played":[74],"role":[77],"classifying":[79],"ads":[81],"extracting":[83],"skills":[84,124],"according":[85],"well-established":[87],"taxonomies.":[88],"However,":[89],"effectiveness":[91],"ML":[93],"depends":[94],"on":[95],"access":[96],"annotated":[98,115],"advertisement":[100],"datasets,":[101],"which":[102,140],"are":[103],"often":[104],"limited":[105],"require":[107],"time-consuming":[108],"manual":[109],"annotation.":[110],"lack":[112],"OJA":[114,122],"benchmarks":[116],"representative":[117],"real":[120,152],"distributions":[125,167],"currently":[127],"limiting":[128],"advances":[129],"intelligence.":[132],"To":[133],"deal":[134],"with":[135],"this,":[136],"we":[137],"propose":[138],"JobGen,":[139],"leverages":[141],"Large":[142],"Language":[143],"Models":[144],"(LLMs)":[145],"generate":[147],"synthetic":[148,180],"OJAs.":[149],"We":[150],"OJAs":[153],"collected":[154],"from":[155],"an":[156],"EU":[157],"project":[158],"ESCO":[161],"taxonomy":[162],"represent":[164],"accurately.":[168],"JobGen":[169],"enhances":[170],"data":[171,181],"diversity":[172],"semantic":[174],"alignment,":[175],"addressing":[176],"common":[177],"issues":[178],"generation.":[182],"resulting":[184],"dataset,":[185],"JobSet,":[186],"provides":[187],"valuable":[189],"resource":[190],"tasks":[192],"like":[193],"extraction":[195],"matching":[198],"openly":[201],"available":[202],"community1.":[205]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}