{"id":"https://openalex.org/W7201853151","doi":"https://doi.org/10.5281/zenodo.21832116","title":"Thai SDG-labelled Text Corpus (v1.0)","display_name":"Thai SDG-labelled Text Corpus (v1.0)","publication_year":2026,"publication_date":"2026-08-07","ids":{"openalex":"https://openalex.org/W7201853151","doi":"https://doi.org/10.5281/zenodo.21832116"},"language":"th","primary_location":{"id":"doi:10.5281/zenodo.21832116","doi":"https://doi.org/10.5281/zenodo.21832116","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21832116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"parent_works":[],"lineage":["https://openalex.org/W7201853151"],"child_works_count":0,"type":"dataset","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.21832116","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146040509","display_name":"Purim Chadarattanathiti","orcid":"https://orcid.org/0009-0009-9996-1154","observed_orcids":["https://orcid.org/0009-0009-9996-1154"]},"institutions":[{"id":"https://openalex.org/I1285782058","display_name":"Rajamangala University of Technology Isan","ror":"https://ror.org/04a2rz655","country_code":"TH","type":"education","lineage":["https://openalex.org/I1285782058"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chadarattanathiti, Purim","raw_affiliation_strings":["Department of Information and Communication Technology, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Thailand"],"raw_orcid":"https://orcid.org/0009-0009-9996-1154","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technology, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Thailand","institution_ids":["https://openalex.org/I1285782058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027213694","display_name":"Yaowaret Jantakat","orcid":"https://orcid.org/0000-0002-4222-741X","observed_orcids":["https://orcid.org/0000-0002-4222-741X"]},"institutions":[{"id":"https://openalex.org/I1285782058","display_name":"Rajamangala University of Technology Isan","ror":"https://ror.org/04a2rz655","country_code":"TH","type":"education","lineage":["https://openalex.org/I1285782058"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Jantakat, Yaowaret","raw_affiliation_strings":["Department of Information and Communication Technology, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Thailand"],"raw_orcid":"https://orcid.org/0000-0002-4222-741X","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technology, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Thailand","institution_ids":["https://openalex.org/I1285782058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030376495","display_name":"Jongkol Janruang","orcid":"https://orcid.org/0009-0002-9132-0570","observed_orcids":["https://orcid.org/0009-0002-9132-0570"]},"institutions":[{"id":"https://openalex.org/I1285782058","display_name":"Rajamangala University of Technology Isan","ror":"https://ror.org/04a2rz655","country_code":"TH","type":"education","lineage":["https://openalex.org/I1285782058"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Janruang, Jongkol","raw_affiliation_strings":["Department of Information and Communication Technology, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Thailand"],"raw_orcid":"https://orcid.org/0009-0002-9132-0570","affiliations":[{"raw_affiliation_string":"Department of Information and Communication Technology, Faculty of Science and Liberal Arts, Rajamangala University of Technology Isan, Thailand","institution_ids":["https://openalex.org/I1285782058"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117400497","display_name":"Jiravadee yoyram","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210091243","display_name":"Buriram Rajabhat University","ror":"https://ror.org/00cgkxv41","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210091243"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Yoyram, Jiravadee","raw_affiliation_strings":["Buriram Rajabhat University"],"raw_orcid":"https://orcid.org/0000-0002-7243-0654","affiliations":[{"raw_affiliation_string":"Buriram Rajabhat University","institution_ids":["https://openalex.org/I4210091243"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5147259768","display_name":"Warinpiphat Watcharapongkasem","orcid":"https://orcid.org/0009-0002-1731-2273","observed_orcids":["https://orcid.org/0009-0002-1731-2273"]},"institutions":[{"id":"https://openalex.org/I4210091243","display_name":"Buriram Rajabhat University","ror":"https://ror.org/00cgkxv41","country_code":"TH","type":"education","lineage":["https://openalex.org/I4210091243"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Watcharapongkasem, Warinpiphat","raw_affiliation_strings":["Buriram Rajabhat University"],"raw_orcid":"https://orcid.org/0009-0002-1731-2273","affiliations":[{"raw_affiliation_string":"Buriram Rajabhat University","institution_ids":["https://openalex.org/I4210091243"]}]}],"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":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5439000129699707,"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":0.5439000129699707,"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":0.31839999556541443,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.057500001043081284,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/sustainable-development-goals","display_name":"Sustainable Development Goals","score":0.9850000143051147},{"id":"https://openalex.org/keywords/thai-language","display_name":"Thai language","score":0.9589999914169312},{"id":"https://openalex.org/keywords/machine-translation","display_name":"machine translation","score":0.6740000247955322},{"id":"https://openalex.org/keywords/human-post-editing","display_name":"human post-editing","score":0.9789999723434448},{"id":"https://openalex.org/keywords/cross-lingual-transfer-learning","display_name":"cross-lingual transfer learning","score":0.7720000147819519},{"id":"https://openalex.org/keywords/sdg-17-partnerships","display_name":"SDG 17 partnerships","score":0.722000002861023},{"id":"https://openalex.org/keywords/synthetic-data-augmentation","display_name":"synthetic data augmentation","score":0.546999990940094},{"id":"https://openalex.org/keywords/quality-control","display_name":"quality control","score":0.4830000102519989},{"id":"https://openalex.org/keywords/inter-annotator-agreement","display_name":"inter-annotator agreement","score":0.8100000023841858}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412999868392944},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.65829998254776},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5702999830245972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5618000030517578},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48829999566078186},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.413100004196167},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.38019999861717224},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.36059999465942383},{"id":"https://openalex.org/C2780560020","wikidata":"https://www.wikidata.org/wiki/Q79719","display_name":"License","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3422999978065491},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C165141518","wikidata":"https://www.wikidata.org/wiki/Q4915126","display_name":"Biomedical text mining","level":3,"score":0.2827000021934509},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2754000127315521},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.257099986076355}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5281/zenodo.21832116","doi":"https://doi.org/10.5281/zenodo.21832116","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21832116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.21832117","doi":"https://doi.org/10.5281/zenodo.21832117","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21832117","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.21835672","doi":"https://doi.org/10.5281/zenodo.21835672","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21835672","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},{"id":"doi:10.5281/zenodo.23182478","doi":"https://doi.org/10.5281/zenodo.23182478","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23182478","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.21832116","doi":"https://doi.org/10.5281/zenodo.21832116","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.21832116","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Dataset"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165397301","https://openalex.org/W4393883842","https://openalex.org/W3206158433","https://openalex.org/W3213250913","https://openalex.org/W6894118097","https://openalex.org/W4327879467","https://openalex.org/W3207386168","https://openalex.org/W4309801933","https://openalex.org/W3031730768","https://openalex.org/W6962795128"],"abstract_inverted_index":{"Thai":[0,6,53,118],"SDG-labelled":[1,7],"Text":[2,8],"Corpus":[3,9],"(v1.0)":[4],"The":[5,24,82,171,233],"is":[10,75,84,173,225,238],"a":[11,55,120],"publicly":[12],"available":[13],"dataset":[14,83,172,224],"for":[15,67,71,110],"Sustainable":[16,218],"Development":[17],"Goal":[18],"(SDG)":[19],"text":[20,204],"classification":[21,205],"in":[22,78,175,251],"Thai.":[23],"corpus":[25],"contains":[26,181],"6,800":[27],"records":[28,36,129,156],"evenly":[29],"balanced":[30],"across":[31],"all":[32],"17":[33,69,128],"SDGs":[34],"(400":[35],"per":[37,158],"goal).":[38],"It":[39],"was":[40],"derived":[41],"from":[42,115],"the":[43,72,79,228,254],"OSDG":[44,235],"Community":[45,236],"Dataset":[46,107,169,237],"(OSDG-CD;":[47],"Zenodo":[48],"DOI:":[49],"10.5281/zenodo.5550238),":[50],"translated":[51,114],"into":[52,117],"through":[54,119],"machine-translation":[56,121],"and":[57,61,89,103,122,133,148,165,177,180,211,245],"human":[58,123],"post-editing":[59,124],"workflow,":[60,125],"augmented":[62],"with":[63,253],"expert-reviewed":[64],"synthetic":[65],"data":[66],"SDG":[68,97,111,127,189,203],"(Partnerships":[70],"Goals),":[73],"which":[74],"not":[76],"included":[77],"original":[80,234],"OSDG-CD.":[81],"intended":[85],"to":[86],"support":[87],"Thai-language":[88,202],"multilingual":[90],"natural":[91],"language":[92],"processing":[93],"(NLP)":[94],"research,":[95],"including":[96],"classification,":[98],"cross-lingual":[99],"learning,":[100],"information":[101],"retrieval,":[102],"policy":[104,212],"document":[105,213],"analysis.":[106],"Construction":[108],"Records":[109],"1\u201316":[112],"were":[113,130],"English":[116],"while":[126],"newly":[131],"generated":[132],"reviewed":[134],"by":[135],"experts.":[136],"Each":[137],"record":[138],"includes":[139,161],"automatic":[140],"quality-control":[141],"indicators":[142,197],"based":[143],"on":[144],"LaBSE":[145],"semantic":[146],"similarity":[147,194],"length-ratio":[149],"checks.":[150],"A":[151],"stratified":[152],"sample":[153],"of":[154],"1,360":[155],"(80":[157],"SDG)":[159],"additionally":[160],"human-expert":[162],"quality":[163],"assessments":[164],"inter-annotator":[166],"agreement":[167],"scores.":[168],"Contents":[170],"distributed":[174,240],"CSV":[176],"XLSX":[178],"formats":[179],"18":[182],"documented":[183],"metadata":[184,192],"fields,":[185],"including:":[186],"Source":[187],"provenance":[188],"labels":[190],"Translation":[191],"Semantic":[193],"scores":[195],"Quality-control":[196],"Expert-review":[198],"outcomes":[199],"Potential":[200],"Applications":[201],"Multilingual":[206],"NLP":[207],"benchmarking":[208],"Research":[209],"funding":[210],"analysis":[214],"Cross-lingual":[215],"transfer":[216],"learning":[217],"development":[219],"analytics":[220],"License":[221],"This":[222],"derivative":[223],"released":[226],"under":[227,241],"CC":[229,242],"BY":[230,243],"4.0":[231],"license.":[232],"also":[239],"4.0,":[244],"appropriate":[246],"attribution":[247],"has":[248],"been":[249],"retained":[250],"accordance":[252],"license":[255],"terms.":[256]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-08T00:00:00"}
