{"id":"https://openalex.org/W4404225543","doi":"https://doi.org/10.3390/bdcc8110153","title":"IndoGovBERT: A Domain-Specific Language Model for Processing Indonesian Government SDG Documents","display_name":"IndoGovBERT: A Domain-Specific Language Model for Processing Indonesian Government SDG Documents","publication_year":2024,"publication_date":"2024-11-09","ids":{"openalex":"https://openalex.org/W4404225543","doi":"https://doi.org/10.3390/bdcc8110153"},"language":"en","primary_location":{"id":"doi:10.3390/bdcc8110153","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8110153","pdf_url":"https://www.mdpi.com/2504-2289/8/11/153/pdf?version=1731484214","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2504-2289/8/11/153/pdf?version=1731484214","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102865282","display_name":"Agus Riyadi","orcid":"https://orcid.org/0000-0002-8807-6864"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]},{"id":"https://openalex.org/I4210150570","display_name":"Ministry of Education and Culture","ror":"https://ror.org/03sxt1c89","country_code":"ID","type":"government","lineage":["https://openalex.org/I4210150570"]}],"countries":["ID","JP"],"is_corresponding":true,"raw_author_name":"Agus Riyadi","raw_affiliation_strings":["Graduate School of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan","Ministry of National Development Planning/BAPPENAS, Jakarta 10310, Indonesia"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]},{"raw_affiliation_string":"Ministry of National Development Planning/BAPPENAS, Jakarta 10310, Indonesia","institution_ids":["https://openalex.org/I4210150570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003233807","display_name":"Mate Kovacs","orcid":"https://orcid.org/0000-0001-5999-8061"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mate Kovacs","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080369483","display_name":"Uwe Serd\u00fclt","orcid":"https://orcid.org/0000-0002-2383-3158"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH","JP"],"is_corresponding":false,"raw_author_name":"Uwe Serd\u00fclt","raw_affiliation_strings":["Center for Democracy Studies Aarau (ZDA), University of Zurich, 8006 Zurich, Switzerland","College of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Democracy Studies Aarau (ZDA), University of Zurich, 8006 Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046742773","display_name":"Victor V. Kryssanov","orcid":"https://orcid.org/0009-0007-6610-5015"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Victor Kryssanov","raw_affiliation_strings":["College of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Ritsumeikan University, Ibaraki 5678570, Osaka, Japan","institution_ids":["https://openalex.org/I135768898"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5102865282"],"corresponding_institution_ids":["https://openalex.org/I135768898","https://openalex.org/I4210150570"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":1.7209,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.87303367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":"8","issue":"11","first_page":"153","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13559","display_name":"Edcuational Technology Systems","score":0.7978000044822693,"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/T13559","display_name":"Edcuational Technology Systems","score":0.7978000044822693,"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/indonesian","display_name":"Indonesian","score":0.9027093648910522},{"id":"https://openalex.org/keywords/indonesian-government","display_name":"Indonesian government","score":0.7411783337593079},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5666055083274841},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5543069839477539},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5405074954032898},{"id":"https://openalex.org/keywords/government","display_name":"Government (linguistics)","score":0.5207203030586243},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3797076344490051},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3532007336616516},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12352454662322998},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.05632743239402771}],"concepts":[{"id":"https://openalex.org/C2779207338","wikidata":"https://www.wikidata.org/wiki/Q9240","display_name":"Indonesian","level":2,"score":0.9027093648910522},{"id":"https://openalex.org/C2993675096","wikidata":"https://www.wikidata.org/wiki/Q20716634","display_name":"Indonesian government","level":3,"score":0.7411783337593079},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5666055083274841},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5543069839477539},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5405074954032898},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.5207203030586243},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3797076344490051},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3532007336616516},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12352454662322998},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.05632743239402771},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/bdcc8110153","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8110153","pdf_url":"https://www.mdpi.com/2504-2289/8/11/153/pdf?version=1731484214","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},{"id":"pmh:doi:10.5167/uzh-268678","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:55ec21ad8a7a49baabd805abf2cfa890","is_oa":true,"landing_page_url":"https://doaj.org/article/55ec21ad8a7a49baabd805abf2cfa890","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":"Big Data and Cognitive Computing, Vol 8, Iss 11, p 153 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/bdcc8110153","is_oa":true,"landing_page_url":"https://doi.org/10.3390/bdcc8110153","pdf_url":"https://www.mdpi.com/2504-2289/8/11/153/pdf?version=1731484214","source":{"id":"https://openalex.org/S4210238752","display_name":"Big Data and Cognitive Computing","issn_l":"2504-2289","issn":["2504-2289"],"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":"Big Data and Cognitive Computing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Partnerships for the goals","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322716","display_name":"Japan International Cooperation Agency","ror":"https://ror.org/022es3t03"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404225543.pdf","grobid_xml":"https://content.openalex.org/works/W4404225543.grobid-xml"},"referenced_works_count":63,"referenced_works":["https://openalex.org/W1999954155","https://openalex.org/W2048489440","https://openalex.org/W2169281690","https://openalex.org/W2181432155","https://openalex.org/W2234451305","https://openalex.org/W2565454157","https://openalex.org/W2572900683","https://openalex.org/W2911489562","https://openalex.org/W2962762220","https://openalex.org/W2971258845","https://openalex.org/W2979826702","https://openalex.org/W3000603264","https://openalex.org/W3023285645","https://openalex.org/W3034238904","https://openalex.org/W3042504460","https://openalex.org/W3048923127","https://openalex.org/W3096466673","https://openalex.org/W3099008231","https://openalex.org/W3099950029","https://openalex.org/W3105564864","https://openalex.org/W3116295307","https://openalex.org/W3116407756","https://openalex.org/W3136145385","https://openalex.org/W3153266325","https://openalex.org/W3166550823","https://openalex.org/W3169392376","https://openalex.org/W3169554260","https://openalex.org/W3177765786","https://openalex.org/W3178709966","https://openalex.org/W3186537269","https://openalex.org/W3199243620","https://openalex.org/W3210174084","https://openalex.org/W3214556263","https://openalex.org/W4210333430","https://openalex.org/W4212984208","https://openalex.org/W4221110890","https://openalex.org/W4226142937","https://openalex.org/W4226418765","https://openalex.org/W4235129393","https://openalex.org/W4236316962","https://openalex.org/W4281257511","https://openalex.org/W4283219089","https://openalex.org/W4285169833","https://openalex.org/W4285190530","https://openalex.org/W4285222437","https://openalex.org/W4285601618","https://openalex.org/W4287887967","https://openalex.org/W4287890137","https://openalex.org/W4303629475","https://openalex.org/W4307254064","https://openalex.org/W4308600709","https://openalex.org/W4312345396","https://openalex.org/W4312729100","https://openalex.org/W4327928778","https://openalex.org/W4328008182","https://openalex.org/W4366698663","https://openalex.org/W4385848332","https://openalex.org/W4387120445","https://openalex.org/W4395047583","https://openalex.org/W6798205730","https://openalex.org/W6810463509","https://openalex.org/W6811297763","https://openalex.org/W6818474068"],"related_works":["https://openalex.org/W3125596490","https://openalex.org/W3121186135","https://openalex.org/W3167898685","https://openalex.org/W4292097865","https://openalex.org/W2377573437","https://openalex.org/W4385612224","https://openalex.org/W3127323648","https://openalex.org/W2490567765","https://openalex.org/W1759598006","https://openalex.org/W2980407885"],"abstract_inverted_index":{"Achieving":[0],"the":[1,65,80,120,144,165,175,180,192,203,213,216,247,266,270,283,299,312,317],"Sustainable":[2],"Development":[3],"Goals":[4],"(SDGs)":[5],"requires":[6],"collaboration":[7,18],"among":[8],"various":[9,157],"stakeholders,":[10],"particularly":[11],"governments":[12,297],"and":[13,37,48,69,73,118,148,210,229,306],"non-state":[14],"actors":[15],"(NSAs).":[16],"This":[17,109],"results":[19],"in":[20,39,179,189,200,225,262,316],"but":[21,196],"is":[22,153,208,222,235],"also":[23,197],"based":[24],"on":[25],"a":[26,40,131,243,256],"continually":[27],"growing":[28],"volume":[29],"of":[30,87,122,160,182,191,202,215,246,269],"documents":[31],"that":[32,282],"needs":[33],"to":[34,114,155,170,291,311],"be":[35,289],"analyzed":[36],"processed":[38],"systematic":[41],"way":[42],"by":[43,164],"government":[44,66,124,184,275],"officials.":[45],"Artificial":[46],"Intelligence":[47],"Natural":[49],"Language":[50],"Processing":[51],"(NLP)":[52],"could,":[53],"thus,":[54],"offer":[55],"valuable":[56],"support":[57],"for":[58,82,102,212,273,296],"progressing":[59],"towards":[60],"SDG":[61,161,276,303],"targets,":[62],"including":[63,93],"automating":[64],"budget":[67],"tagging":[68],"classifying":[70],"NSA":[71],"requests":[72],"initiatives,":[74],"as":[75,77,252,254],"well":[76,253],"helping":[78],"uncover":[79],"possibilities":[81],"matching":[83],"these":[84],"two":[85],"categories":[86],"activities.":[88],"Many":[89],"non-English":[90],"speaking":[91],"countries,":[92],"Indonesia,":[94],"however,":[95],"face":[96,302],"limited":[97],"NLP":[98,308],"resources,":[99],"such":[100],"as,":[101],"instance,":[103],"domain-specific":[104,141],"pre-trained":[105],"language":[106,241],"models":[107],"(PTLMs).":[108],"circumstance":[110],"makes":[111],"it":[112,234],"difficult":[113],"automate":[115,156],"document":[116,162,277,304],"processing":[117,163,305],"improve":[119],"efficacy":[121],"SDG-related":[123],"efforts.":[125],"The":[126,151,186,219,279],"presented":[127,318],"study":[128],"introduces":[129],"IndoGovBERT,":[130],"Bidirectional":[132],"Encoder":[133],"Representations":[134],"from":[135,174],"Transformers":[136],"(BERT)-based":[137],"PTLM":[138,171,285],"built":[139],"with":[140,237,255,315],"corpora,":[142],"leveraging":[143],"Indonesian":[145,166,239,274],"government\u2019s":[146],"public":[147],"internal":[149],"documents.":[150],"model":[152,194,221,272],"intended":[154],"laborious":[158],"tasks":[159],"government.":[167],"Different":[168],"approaches":[169],"development":[172,214,286],"known":[173],"literature":[176],"are":[177],"examined":[178],"context":[181],"typical":[183],"settings.":[185],"most":[187,198],"effective,":[188],"terms":[190,201],"resultant":[193],"performance,":[195],"efficient,":[199],"computational":[204],"resources":[205],"required,":[206],"methodology":[207,287],"determined":[209],"deployed":[211],"IndoGovBERT":[217,271],"model.":[218,259],"developed":[220],"then":[223],"scrutinized":[224],"several":[226],"text":[227],"classification":[228],"similarity":[230],"assessment":[231],"experiments,":[232],"where":[233],"compared":[236],"four":[238],"general-purpose":[240],"models,":[242],"non-transformer":[244],"approach":[245],"Multilabel":[248],"Topic":[249],"Model":[250],"(MLTM),":[251],"Multilingual":[257],"BERT":[258],"Results":[260],"obtained":[261],"all":[263],"experiments":[264],"highlight":[265],"superior":[267],"capability":[268],"processing.":[278],"latter":[280],"suggests":[281],"proposed":[284],"could":[288],"adopted":[290],"build":[292],"high-performance":[293],"specialized":[294],"PTLMs":[295],"around":[298],"globe":[300],"which":[301],"other":[307],"challenges":[309],"similar":[310],"ones":[313],"dealt":[314],"study.":[319]},"counts_by_year":[{"year":2025,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
