{"id":"W4376274788","doi":"10.1016/j.prevetmed.2023.105932","title":"Animal disease surveillance: How to represent textual data for classifying epidemiological information","year":2023,"lang":"en","type":"article","venue":"Preventive Veterinary Medicine","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Sherbrooke","funders":"Centre de Coopération Internationale en Recherche Agronomique pour le Développement; Agence Nationale de la Recherche; European Commission","keywords":"Relevance (law); Context (archaeology); Computer science; Representation (politics); Word (group theory); Natural language processing; Artificial intelligence; Binary classification; Information retrieval; Data science; Mathematics; Support vector machine; Geography","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002956329,0.001033228,0.0006062858,0.004630586,0.0002846422,0.002436431,0.0008522669,0.001123522,0.001614665],"category_scores_gemma":[0.01912508,0.0002318082,0.0006800531,0.002515922,0.0003824756,0.004781574,0.0008002376,0.0009430476,0.001578959],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00074569,"about_ca_system_score_gemma":0.000740367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002732507,"about_ca_topic_score_gemma":0.00293437,"domain_scores_codex":[0.9985494,0.000763779,0.0001897108,0.0002399652,0.0001906931,0.00006639704],"domain_scores_gemma":[0.9905915,0.005884113,0.0009772488,0.001032393,0.001331651,0.0001830093],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005806469,0.0006696858,0.02008628,0.001253393,0.0002165476,0.0001464315,0.0006603866,0.0286076,0.02235288,0.005258277,0.01149272,0.908675],"study_design_scores_gemma":[0.0001118711,0.0005648857,0.01479546,0.0005622045,0.0002146708,0.0003359735,0.001072813,0.9080551,0.02198188,0.03380363,0.01836604,0.0001355669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2351207,0.004342704,0.7252939,0.005774897,0.0006597419,0.001014879,0.01600987,0.006711492,0.005071807],"genre_scores_gemma":[0.5408387,0.001279002,0.4438865,0.0003676629,0.0003002114,0.0005942683,0.01128138,0.0001415041,0.001310717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004630586,"threshold_uncertainty_score":0.01563478,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1931269320748563,"score_gpt":0.419078500008632,"score_spread":0.2259515679337757,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}