{"id":"https://openalex.org/W4366826292","doi":"https://doi.org/10.3390/data8050074","title":"MN-DS: A Multilabeled News Dataset for News Articles Hierarchical Classification","display_name":"MN-DS: A Multilabeled News Dataset for News Articles Hierarchical Classification","publication_year":2023,"publication_date":"2023-04-23","ids":{"openalex":"https://openalex.org/W4366826292","doi":"https://doi.org/10.3390/data8050074"},"language":"en","primary_location":{"id":"doi:10.3390/data8050074","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data8050074","pdf_url":"https://www.mdpi.com/2306-5729/8/5/74/pdf?version=1682252494","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"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":"Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2306-5729/8/5/74/pdf?version=1682252494","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059422270","display_name":"Alina Petukhova","orcid":"https://orcid.org/0000-0002-0652-6068"},"institutions":[{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Alina Petukhova","raw_affiliation_strings":["COPELABS, Lus\u00f3fona University, Campo Grande 376, 1749-024 Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-0652-6068","affiliations":[{"raw_affiliation_string":"COPELABS, Lus\u00f3fona University, Campo Grande 376, 1749-024 Lisbon, Portugal","institution_ids":["https://openalex.org/I88596544"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036991749","display_name":"Nuno Fachada","orcid":"https://orcid.org/0000-0002-8487-5837"},"institutions":[{"id":"https://openalex.org/I88596544","display_name":"Universidade Lus\u00f3fona","ror":"https://ror.org/05xxfer42","country_code":"PT","type":"education","lineage":["https://openalex.org/I88596544"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Fachada","raw_affiliation_strings":["COPELABS, Lus\u00f3fona University, Campo Grande 376, 1749-024 Lisbon, Portugal"],"raw_orcid":"https://orcid.org/0000-0002-8487-5837","affiliations":[{"raw_affiliation_string":"COPELABS, Lus\u00f3fona University, Campo Grande 376, 1749-024 Lisbon, Portugal","institution_ids":["https://openalex.org/I88596544"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5059422270"],"corresponding_institution_ids":["https://openalex.org/I88596544"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1732},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1732},"fwci":1.5337,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85734022,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"8","issue":"5","first_page":"74","last_page":"74"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9962000250816345,"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":0.994700014591217,"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/structuring","display_name":"Structuring","score":0.7136220335960388},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6323641538619995},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.56059730052948},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49220314621925354},{"id":"https://openalex.org/keywords/news-analytics","display_name":"News analytics","score":0.4157024323940277},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19819855690002441},{"id":"https://openalex.org/keywords/political-science","display_name":"Political science","score":0.07974624633789062},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.04404553771018982}],"concepts":[{"id":"https://openalex.org/C2775945657","wikidata":"https://www.wikidata.org/wiki/Q381442","display_name":"Structuring","level":2,"score":0.7136220335960388},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6323641538619995},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.56059730052948},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49220314621925354},{"id":"https://openalex.org/C103648661","wikidata":"https://www.wikidata.org/wiki/Q7019453","display_name":"News analytics","level":2,"score":0.4157024323940277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19819855690002441},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.07974624633789062},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.04404553771018982},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/data8050074","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data8050074","pdf_url":"https://www.mdpi.com/2306-5729/8/5/74/pdf?version=1682252494","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"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":"Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c14e9b3f4d6242c888b3f24f75485a1f","is_oa":true,"landing_page_url":"https://doaj.org/article/c14e9b3f4d6242c888b3f24f75485a1f","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":"Data, Vol 8, Iss 5, p 74 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2306-5729/8/5/74/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/data8050074","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Data; Volume 8; Issue 5; Pages: 74","raw_type":"Text"},{"id":"pmh:oai:recil.ensinolusofona.pt:10437/13813","is_oa":true,"landing_page_url":"http://hdl.handle.net/10437/13813","pdf_url":null,"source":{"id":"https://openalex.org/S4306402401","display_name":"Reposit\u00f3rio Cient\u00edfico Lus\u00f3fona (Grupo Lus\u00f3fona)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.3390/data8050074","is_oa":true,"landing_page_url":"https://doi.org/10.3390/data8050074","pdf_url":"https://www.mdpi.com/2306-5729/8/5/74/pdf?version=1682252494","source":{"id":"https://openalex.org/S4210226510","display_name":"Data","issn_l":"2306-5729","issn":["2306-5729"],"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":"Data","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.46000000834465027}],"awards":[{"id":"https://openalex.org/G6120445142","display_name":null,"funder_award_id":"UIDB/04111/2020","funder_id":"https://openalex.org/F4320334779","funder_display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia"}],"funders":[{"id":"https://openalex.org/F4320334779","display_name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","ror":"https://ror.org/00snfqn58"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4366826292.pdf"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W1680797894","https://openalex.org/W2101234009","https://openalex.org/W2150766729","https://openalex.org/W2250539671","https://openalex.org/W2589272824","https://openalex.org/W2903950532","https://openalex.org/W2963274420","https://openalex.org/W2979826702","https://openalex.org/W3152272674","https://openalex.org/W3212464620","https://openalex.org/W4213009331","https://openalex.org/W4239510810","https://openalex.org/W4310969328","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W4251394462","https://openalex.org/W1580673008","https://openalex.org/W1510936208","https://openalex.org/W2486167009","https://openalex.org/W1595575899","https://openalex.org/W756498608","https://openalex.org/W2135201366","https://openalex.org/W4285395220","https://openalex.org/W2131947708"],"abstract_inverted_index":{"This":[0,39,56],"article":[1],"presents":[2],"a":[3,29],"dataset":[4,40,57],"of":[5],"10,917":[6],"news":[7,11,52,65],"articles":[8,26,53],"with":[9,32],"hierarchical":[10,30],"categories":[12],"collected":[13],"between":[14],"1":[15],"January":[16],"2019":[17],"and":[18,35,68],"31":[19],"December":[20],"2019.":[21],"We":[22],"manually":[23],"labeled":[24],"the":[25],"based":[27,72],"on":[28,64,73],"taxonomy":[31],"17":[33],"first-level":[34],"109":[36],"second-level":[37],"categories.":[38],"can":[41,58],"be":[42,59],"used":[43],"to":[44],"train":[45],"machine":[46],"learning":[47],"models":[48],"for":[49,61],"automatically":[50],"classifying":[51],"by":[54],"topic.":[55],"helpful":[60],"researchers":[62],"working":[63],"structuring,":[66],"classification,":[67],"predicting":[69],"future":[70],"events":[71],"released":[74],"news.":[75]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2026-01-25T23:04:38.658462","created_date":"2023-04-25T00:00:00"}
