{"id":"https://openalex.org/W7150853798","doi":"https://doi.org/10.1016/j.eswa.2026.132345","title":"Enhancing language models with selective masking for thematic and misinformation classification in a One Health context","display_name":"Enhancing language models with selective masking for thematic and misinformation classification in a One Health context","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7150853798","doi":"https://doi.org/10.1016/j.eswa.2026.132345"},"language":"en","primary_location":{"id":"doi:10.1016/j.eswa.2026.132345","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132345","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1016/j.eswa.2026.132345","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130379813","display_name":"Youssef Mahdoubi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119856","display_name":"Universit\u00e9 Sultan Moulay Slimane","ror":"https://ror.org/02m8tb249","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210119856"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Youssef Mahdoubi","raw_affiliation_strings":["Faculty of Science and Techniques, IDC Team, Sultan Moulay Slimane University, Beni-Mellal, Morocco"],"raw_orcid":"https://orcid.org/0009-0001-8333-0958","affiliations":[{"raw_affiliation_string":"Faculty of Science and Techniques, IDC Team, Sultan Moulay Slimane University, Beni-Mellal, Morocco","institution_ids":["https://openalex.org/I4210119856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076369751","display_name":"Najlae Idrissi","orcid":"https://orcid.org/0000-0003-0038-2988"},"institutions":[{"id":"https://openalex.org/I4210119856","display_name":"Universit\u00e9 Sultan Moulay Slimane","ror":"https://ror.org/02m8tb249","country_code":"MA","type":"education","lineage":["https://openalex.org/I4210119856"]}],"countries":["MA"],"is_corresponding":false,"raw_author_name":"Najlae Idrissi","raw_affiliation_strings":["Faculty of Science and Techniques, IDC Team, Sultan Moulay Slimane University, Beni-Mellal, Morocco"],"raw_orcid":"https://orcid.org/0000-0003-0038-2988","affiliations":[{"raw_affiliation_string":"Faculty of Science and Techniques, IDC Team, Sultan Moulay Slimane University, Beni-Mellal, Morocco","institution_ids":["https://openalex.org/I4210119856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123501968","display_name":"Mathieu ROCHE","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I131077856","display_name":"Centre de Coop\u00e9ration Internationale en Recherche Agronomique pour le D\u00e9veloppement","ror":"https://ror.org/05kpkpg04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I131077856"]},{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]},{"id":"https://openalex.org/I22248866","display_name":"AgroParisTech","ror":"https://ror.org/02kbmgc12","country_code":"FR","type":"education","lineage":["https://openalex.org/I22248866","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210088668","display_name":"Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement","ror":"https://ror.org/003vg9w96","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210088668"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Roche","raw_affiliation_strings":["CIRAD, UMR TETIS, Montpellier, F-34398, France","TETIS, Univ Montpellier, AgroParisTech, CIRAD, CNRS, INRAE, Montpellier, France"],"raw_orcid":"https://orcid.org/0000-0003-3272-8568","affiliations":[{"raw_affiliation_string":"CIRAD, UMR TETIS, Montpellier, F-34398, France","institution_ids":["https://openalex.org/I131077856"]},{"raw_affiliation_string":"TETIS, Univ Montpellier, AgroParisTech, CIRAD, CNRS, INRAE, Montpellier, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I131077856","https://openalex.org/I19894307","https://openalex.org/I22248866","https://openalex.org/I4210088668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043379601","display_name":"Sarah Valentin","orcid":"https://orcid.org/0000-0002-9028-681X"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I131077856","display_name":"Centre de Coop\u00e9ration Internationale en Recherche Agronomique pour le D\u00e9veloppement","ror":"https://ror.org/05kpkpg04","country_code":"FR","type":"facility","lineage":["https://openalex.org/I131077856"]},{"id":"https://openalex.org/I19894307","display_name":"Universit\u00e9 de Montpellier","ror":"https://ror.org/051escj72","country_code":"FR","type":"education","lineage":["https://openalex.org/I19894307"]},{"id":"https://openalex.org/I22248866","display_name":"AgroParisTech","ror":"https://ror.org/02kbmgc12","country_code":"FR","type":"education","lineage":["https://openalex.org/I22248866","https://openalex.org/I277688954"]},{"id":"https://openalex.org/I4210088668","display_name":"Institut National de Recherche pour l'Agriculture, l'Alimentation et l'Environnement","ror":"https://ror.org/003vg9w96","country_code":"FR","type":"government","lineage":["https://openalex.org/I4210088668"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Sarah Valentin","raw_affiliation_strings":["CIRAD, UMR TETIS, Montpellier, F-34398, France","TETIS, Univ Montpellier, AgroParisTech, CIRAD, CNRS, INRAE, Montpellier, France"],"raw_orcid":"https://orcid.org/0000-0002-9028-681X","affiliations":[{"raw_affiliation_string":"CIRAD, UMR TETIS, Montpellier, F-34398, France","institution_ids":["https://openalex.org/I131077856"]},{"raw_affiliation_string":"TETIS, Univ Montpellier, AgroParisTech, CIRAD, CNRS, INRAE, Montpellier, France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I131077856","https://openalex.org/I19894307","https://openalex.org/I22248866","https://openalex.org/I4210088668"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5043379601"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I131077856","https://openalex.org/I19894307","https://openalex.org/I22248866","https://openalex.org/I4210088668"],"apc_list":{"value":3500,"currency":"USD","value_usd":3500},"apc_paid":{"value":3500,"currency":"USD","value_usd":3500},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.31205667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"322","issue":null,"first_page":"132345","last_page":"132345"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.7633000016212463,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.7633000016212463,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10833","display_name":"Vaccine Coverage and Hesitancy","score":0.023099999874830246,"subfield":{"id":"https://openalex.org/subfields/3306","display_name":"Health"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.0210999995470047,"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/misinformation","display_name":"Misinformation","score":0.8637999892234802},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.6858999729156494},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6581000089645386},{"id":"https://openalex.org/keywords/thematic-map","display_name":"Thematic map","score":0.44510000944137573},{"id":"https://openalex.org/keywords/thematic-analysis","display_name":"Thematic analysis","score":0.4300000071525574},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3601999878883362}],"concepts":[{"id":"https://openalex.org/C2776990098","wikidata":"https://www.wikidata.org/wiki/Q13579947","display_name":"Misinformation","level":2,"score":0.8637999892234802},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7074999809265137},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.6858999729156494},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6581000089645386},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5819000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4975999891757965},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.44510000944137573},{"id":"https://openalex.org/C74196892","wikidata":"https://www.wikidata.org/wiki/Q7781188","display_name":"Thematic analysis","level":3,"score":0.4300000071525574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.3273000121116638},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3102000057697296},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2922999858856201},{"id":"https://openalex.org/C3017977704","wikidata":"https://www.wikidata.org/wiki/Q18745135","display_name":"Health data","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25929999351501465}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1016/j.eswa.2026.132345","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132345","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},{"id":"pmh:oai:agritrop.cirad.fr:617922","is_oa":true,"landing_page_url":"http://agritrop.cirad.fr/617922/","pdf_url":"http://agritrop.cirad.fr/617922/3/1-s2.0-S0957417426012583-main.pdf","source":{"id":"https://openalex.org/S4306402311","display_name":"Agritrop (Cirad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I131077856","host_organization_name":"Centre de Coop\u00e9ration Internationale en Recherche Agronomique pour le D\u00e9veloppement","host_organization_lineage":["https://openalex.org/I131077856"],"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":"Expert Systems with Applications","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:HAL:hal-05670318v1","is_oa":true,"landing_page_url":"https://hal.science/hal-05670318","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"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":"Expert Systems with Applications, 2026, 322, pp.132345. &#x27E8;10.1016/j.eswa.2026.132345&#x27E9;","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1016/j.eswa.2026.132345","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.eswa.2026.132345","pdf_url":null,"source":{"id":"https://openalex.org/S13144211","display_name":"Expert Systems with Applications","issn_l":"0957-4174","issn":["0957-4174","1873-6793"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Expert Systems with Applications","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5850868821144104,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G5212034770","display_name":"Building epidemiological surveillance and prophylaxis with observations both near and distant","funder_award_id":"ANR-20-PCPA-0002","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320323771","display_name":"Centre National pour la Recherche Scientifique et Technique","ror":"https://ror.org/00675rp98"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2012783767","https://openalex.org/W2101746535","https://openalex.org/W2889326414","https://openalex.org/W2911489562","https://openalex.org/W3034942609","https://openalex.org/W4200277663","https://openalex.org/W4365504037","https://openalex.org/W4394564251"],"related_works":[],"abstract_inverted_index":{"The":[0,103],"objective":[1],"of":[2,10,18,119,126,175,208,236],"this":[3,70],"paper":[4],"is":[5],"to":[6,61,65,161,171,249],"address":[7,36],"the":[8,16,50,63,109,112,124,137,149,173,206,209,237],"scarcity":[9],"labeled":[11,33,120,222],"textual":[12],"data":[13],"and":[14,92,153,157,186,231],"improve":[15],"performance":[17,174,207],"language":[19,46,180,210],"models":[20,211],"in":[21,48,145,205,215,233],"classification":[22,114,213,228],"tasks":[23,214],"within":[24,136],"a":[25,41,66,244],"One":[26,138,164],"Health":[27,139,165],"context":[28],"by":[29,56],"using":[30,116,178,229],"small":[31,117],"domain-specific":[32],"corpora.":[34],"To":[35,122],"these":[37],"challenges,":[38],"we":[39,72,129,189,242],"propose":[40,73],"two-phase":[42],"training":[43],"pipeline":[44],"for":[45,111],"models,":[47],"which":[49,79,94],"first":[51],"phase":[52,105],"involves":[53],"post-training":[54],"guided":[55],"selective":[57],"masking":[58,76],"(SM)":[59],"strategies":[60],"adapt":[62],"model":[64,110],"specific":[67],"domain.":[68],"For":[69],"purpose,":[71],"two":[74,132],"novel":[75],"strategies:":[77],"SM-Lex-TFIDF,":[78],"masks":[80,95],"domain":[81],"lexicon":[82,97],"terms":[83,98],"with":[84,99,193,220],"high":[85,100],"TF-IDF":[86,101],"(term":[87],"frequency-inverse":[88],"document":[89],"frequency)":[90],"values,":[91],"SM-NonLex-TFIDF,":[93],"non-domain":[96],"values.":[102],"second":[104],"focuses":[106],"on":[107,131],"fine-tuning":[108],"target":[113],"task":[115],"amounts":[118],"data.":[121,223],"demonstrate":[123,202],"effectiveness":[125],"our":[127,176,191],"approach,":[128],"focus":[130],"related":[133],"application":[134],"areas":[135],"context,":[140],"i.e.,":[141],"(i)":[142],"thematic":[143],"content":[144],"integrated":[146],"health,":[147,152],"covering":[148],"biomedical,":[150],"plant":[151],"syndromic":[154],"surveillance":[155],"domains,":[156],"(ii)":[158],"epidemic":[159],"misinformation,":[160],"achieve":[162],"improved":[163],"monitoring.":[166],"We":[167],"conduct":[168],"extensive":[169],"evaluations":[170],"assess":[172],"approach":[177,225],"three":[179],"models:":[181],"BERT":[182],"Base":[183],",":[184],"SciBERT,":[185],"BioBERT.":[187],"Additionally,":[188],"compare":[190],"method":[192],"low-resource":[194],"LLM-based":[195],"approaches,":[196],"including":[197],"zero/few-shot":[198,227],"classification.":[199],"Experimental":[200],"results":[201],"significant":[203],"improvements":[204],"across":[212],"both":[216],"targeted":[217],"areas,":[218],"even":[219],"limited":[221],"Our":[224],"outperforms":[226],"LLaMA-3.1-8B":[230],"Mistral-7B":[232],"four":[234],"out":[235],"five":[238],"datasets":[239],"evaluated.":[240],"Furthermore,":[241],"provide":[243],"summary":[245],"mapping":[246],"each":[247],"strategy":[248],"its":[250],"most":[251],"effective":[252],"context.":[253]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-04-07T00:00:00"}
