{"id":"https://openalex.org/W4322714432","doi":"https://doi.org/10.63317/43229qwkm5h2","title":"Enriching Epidemiological Thematic Features For Disease Surveillance Corpora Classification","display_name":"Enriching Epidemiological Thematic Features For Disease Surveillance Corpora Classification","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4322714432","doi":"https://doi.org/10.63317/43229qwkm5h2"},"language":"en","primary_location":{"id":"doi:10.63317/43229qwkm5h2","doi":"https://doi.org/10.63317/43229qwkm5h2","is_oa":false,"landing_page_url":"https://doi.org/10.63317/43229qwkm5h2","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://agritrop.cirad.fr/601462/","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023018145","display_name":"Edmond Odhiambo Menya","orcid":"https://orcid.org/0000-0001-7408-1710","observed_orcids":["https://orcid.org/0000-0001-7408-1710"]},"institutions":[{"id":"https://openalex.org/I161372803","display_name":"Strathmore University","ror":"https://ror.org/047dnqw48","country_code":"KE","type":"education","lineage":["https://openalex.org/I161372803"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Edmond Menya","raw_affiliation_strings":["Strathmore University [Nairobi] (Kenya)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Strathmore University [Nairobi] (Kenya)","institution_ids":["https://openalex.org/I161372803"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014118555","display_name":"Mathieu Roche A","orcid":"https://orcid.org/0000-0003-3272-8568","observed_orcids":["https://orcid.org/0000-0003-3272-8568"]},"institutions":[{"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/I4387153996","display_name":"Territoires, Environnement, T\u00e9l\u00e9d\u00e9tection et Information Spatiale","ror":"https://ror.org/0458hw939","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I131077856","https://openalex.org/I22248866","https://openalex.org/I277688954","https://openalex.org/I4210088668","https://openalex.org/I4387153996"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mathieu Roche","raw_affiliation_strings":["Cirad-ES - D\u00e9partement Environnements et Soci\u00e9t\u00e9s (Campus international de Baillarguet TA C-DIR / B 34398 Montpellier Cedex 5 France - France)","UMR TETIS - Territoires, Environnement, T\u00e9l\u00e9d\u00e9tection et Information Spatiale (Maison de la t\u00e9l\u00e9d\u00e9tection - 500 rue Jean-Fran\u00e7ois Breton - 34093 Montpellier Cedex 5 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cirad-ES - D\u00e9partement Environnements et Soci\u00e9t\u00e9s (Campus international de Baillarguet TA C-DIR / B 34398 Montpellier Cedex 5 France - France)","institution_ids":["https://openalex.org/I131077856"]},{"raw_affiliation_string":"UMR TETIS - Territoires, Environnement, T\u00e9l\u00e9d\u00e9tection et Information Spatiale (Maison de la t\u00e9l\u00e9d\u00e9tection - 500 rue Jean-Fran\u00e7ois Breton - 34093 Montpellier Cedex 5 - France)","institution_ids":["https://openalex.org/I4387153996"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041660039","display_name":"Roberto Interdonato","orcid":"https://orcid.org/0000-0002-0536-6277","observed_orcids":["https://orcid.org/0000-0002-0536-6277"]},"institutions":[{"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/I4387153996","display_name":"Territoires, Environnement, T\u00e9l\u00e9d\u00e9tection et Information Spatiale","ror":"https://ror.org/0458hw939","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I131077856","https://openalex.org/I22248866","https://openalex.org/I277688954","https://openalex.org/I4210088668","https://openalex.org/I4387153996"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Roberto Interdonato","raw_affiliation_strings":["Cirad-ES - D\u00e9partement Environnements et Soci\u00e9t\u00e9s (Campus international de Baillarguet TA C-DIR / B 34398 Montpellier Cedex 5 France - France)","UMR TETIS - Territoires, Environnement, T\u00e9l\u00e9d\u00e9tection et Information Spatiale (Maison de la t\u00e9l\u00e9d\u00e9tection - 500 rue Jean-Fran\u00e7ois Breton - 34093 Montpellier Cedex 5 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cirad-ES - D\u00e9partement Environnements et Soci\u00e9t\u00e9s (Campus international de Baillarguet TA C-DIR / B 34398 Montpellier Cedex 5 France - France)","institution_ids":["https://openalex.org/I131077856"]},{"raw_affiliation_string":"UMR TETIS - Territoires, Environnement, T\u00e9l\u00e9d\u00e9tection et Information Spatiale (Maison de la t\u00e9l\u00e9d\u00e9tection - 500 rue Jean-Fran\u00e7ois Breton - 34093 Montpellier Cedex 5 - France)","institution_ids":["https://openalex.org/I4387153996"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034369274","display_name":"Dickson Odhiambo Owuor","orcid":"https://orcid.org/0000-0002-0968-5742","observed_orcids":["https://orcid.org/0000-0002-0968-5742","https://orcid.org/0009-0009-0553-7302"]},"institutions":[{"id":"https://openalex.org/I161372803","display_name":"Strathmore University","ror":"https://ror.org/047dnqw48","country_code":"KE","type":"education","lineage":["https://openalex.org/I161372803"]}],"countries":["KE"],"is_corresponding":false,"raw_author_name":"Dickson Owuor","raw_affiliation_strings":["Strathmore University [Nairobi] (Kenya)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Strathmore University [Nairobi] (Kenya)","institution_ids":["https://openalex.org/I161372803"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1068,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.3701705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"3741","last_page":"3750"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6089000105857849,"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":0.6089000105857849,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.2581000030040741,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.054099999368190765,"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/disease-surveillance","display_name":"disease surveillance","score":0.9369999766349792},{"id":"https://openalex.org/keywords/animal-disease-outbreaks","display_name":"animal disease outbreaks","score":0.8970000147819519},{"id":"https://openalex.org/keywords/biomedical-language-models","display_name":"biomedical language models","score":0.6669999957084656},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8199999928474426},{"id":"https://openalex.org/keywords/information-extraction","display_name":"information extraction","score":0.4860000014305115},{"id":"https://openalex.org/keywords/ablation-study","display_name":"ablation study","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7015705108642578},{"id":"https://openalex.org/C93692415","wikidata":"https://www.wikidata.org/wiki/Q1502030","display_name":"Thematic map","level":2,"score":0.6998038291931152},{"id":"https://openalex.org/C107130276","wikidata":"https://www.wikidata.org/wiki/Q133805","display_name":"Epidemiology","level":2,"score":0.49743011593818665},{"id":"https://openalex.org/C2776480101","wikidata":"https://www.wikidata.org/wiki/Q3555250","display_name":"Disease surveillance","level":3,"score":0.43515244126319885},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3713908791542053},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.18080765008926392},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.16676297783851624},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.15297949314117432},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.06399780511856079}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/43229qwkm5h2","doi":"https://doi.org/10.63317/43229qwkm5h2","is_oa":false,"landing_page_url":"https://doi.org/10.63317/43229qwkm5h2","pdf_url":null,"source":{"id":"https://openalex.org/S7407088301","display_name":"Language Resources and Evaluation Conference (LREC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:agritrop.cirad.fr:601462","doi":null,"is_oa":true,"landing_page_url":"http://agritrop.cirad.fr/601462/","pdf_url":null,"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,"listed_in":[],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Language Resources and Evaluation Conference","raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:HAL:hal-04006003v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.inrae.fr/hal-04006003","pdf_url":"https://hal.inrae.fr/hal-04006003v1/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"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":"LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, Jun 2022, Marseille, France. pp.3741","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:agritrop.cirad.fr:601462","doi":null,"is_oa":true,"landing_page_url":"http://agritrop.cirad.fr/601462/","pdf_url":null,"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,"listed_in":[],"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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th Language Resources and Evaluation Conference","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6201598102","display_name":"MOnitoring Outbreak events for Disease surveillance in a data science context","funder_award_id":"874850","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4322714432.pdf","grobid_xml":"https://content.openalex.org/works/W4322714432.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W2984147501"],"related_works":["https://openalex.org/W4393972641","https://openalex.org/W4402655133","https://openalex.org/W4376274788","https://openalex.org/W4416124213","https://openalex.org/W3117022592","https://openalex.org/W4405205852","https://openalex.org/W4200277663","https://openalex.org/W4416620277","https://openalex.org/W4399693640","https://openalex.org/W2888787635"],"abstract_inverted_index":{"We":[0,33,90,109,168],"present":[1],"EpidBioBERT,":[2,152],"a":[3,35,61,92,98,122,175],"biosurveillance":[4],"epidemiological":[5,47,66,71,87,106,118],"document":[6,67,88,119],"tagger":[7],"for":[8,53,195],"disease":[9,143],"surveillance":[10,144],"over":[11,121,206],"PADI-Web":[12,19,130,221],"system.":[13],"Our":[14,58,199],"model":[15,96,178,180,200],"is":[16],"trained":[17],"on":[18,25,45,142,162,187,217,219],"corpus":[20],"which":[21,80],"contains":[22],"news":[23],"articles":[24],"Animal":[26],"Diseases":[27],"Outbreak":[28],"extracted":[29],"from":[30],"the":[31,134,155,163,220,226],"web.":[32],"train":[34],"classifier":[36,164,222],"to":[37,64,85,116,137],"discriminate":[38],"between":[39],"relevant":[40],"and":[41,78],"irrelevant":[42],"documents":[43,190],"based":[44,179],"their":[46],"thematic":[48,72,107,112,160,183],"feature":[49,161,184],"content":[50],"in":[51,129,151],"preparation":[52],"further":[54,147],"epidemiology":[55,159,196],"information":[56,149],"extraction.":[57],"approach":[59,102,173],"proposes":[60],"new":[62],"way":[63],"perform":[65],"classification":[68,120,197],"by":[69],"enriching":[70],"features":[73,113],"namely":[74],"disease,":[75],"host,":[76],"location":[77],"date,":[79],"are":[81,191],"used":[82,128],"as":[83],"inputs":[84],"our":[86,170],"classifier.":[89,131],"adopt":[91],"pre-trained":[93,172,186],"biomedical":[94,171],"language":[95,177],"with":[97,174,211,223],"novel":[99],"fine":[100],"tuning":[101],"that":[103,182],"enriches":[104],"these":[105,111],"features.":[108],"find":[110],"rich":[114,193],"enough":[115,194],"improve":[117],"smaller":[123],"data":[124,228],"set":[125],"than":[126],"initially":[127],"This":[132],"improves":[133],"classifiers":[135],"ability":[136],"avoid":[138],"false":[139],"positive":[140],"alerts":[141],"systems.":[145],"To":[146],"understand":[148],"encoded":[150],"we":[153],"experiment":[154],"impact":[156],"of":[157,204,214],"each":[158],"under":[165],"ablation":[166],"studies.":[167],"compare":[169],"general":[176,188],"finding":[181],"embeddings":[185],"English":[189],"not":[192],"task.":[198],"achieves":[201],"an":[202,207,212],"F1-score":[203],"95.5%":[205],"unseen":[208],"test":[209],"set,":[210],"improvement":[213],"+5.5":[215],"points":[216],"F1-Score":[218],"nearly":[224],"half":[225],"training":[227],"set.":[229]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2023-03-02T00:00:00"}
