{"id":"W6977186955","doi":"10.60692/w04d5-xe375","title":"Feature Selection for an Explainability Analysis in Detection of COVID-19 Active Cases from Facebook User-Based Online Surveys","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Feature selection; Boosting (machine learning); Gradient boosting; Random forest; Binary classification; Ranking (information retrieval); Receiver operating characteristic; Pattern recognition (psychology); Feature (linguistics); Binary number","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":{"n_in":0,"stratum":"about_only","weight":3321.24,"opus":{"tier":"OUT","genre":"empirical","about_ca":false,"confidence":"high","reason":"Machine learning detection of COVID-19 cases from survey data."},"gpt":{"tier":"OUT","genre":"empirical","about_ca":false,"confidence":"high","reason":"It develops a machine-learning model for detecting COVID-19 cases."},"grok":{"tier":"OUT","genre":"empirical","about_ca":false,"confidence":"high","reason":"ML detection of COVID-19 from survey data is applied epidemiology/AI, not metaresearch."}},"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005401264,0.0005822135,0.0009293637,0.005325351,0.0003860645,0.0009245106,0.0006642605,0.0006156526,0.001152757],"category_scores_gemma":[0.01566285,0.0001485541,0.0008987414,0.001864786,0.0003012045,0.0008214082,0.0007836807,0.0006387329,0.0003652298],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003855586,"about_ca_system_score_gemma":0.0004867349,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001723508,"about_ca_topic_score_gemma":0.001731451,"domain_scores_codex":[0.9974211,0.001159782,0.0002457884,0.0004013841,0.0005407832,0.0002311513],"domain_scores_gemma":[0.988385,0.008361194,0.001328002,0.0005634147,0.001133588,0.0002288585],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000570083,0.0005986536,0.6690937,0.0002771106,0.0004340279,0.0003509509,0.0003996631,0.01389051,0.004764079,0.001427368,0.004933467,0.3032604],"study_design_scores_gemma":[0.00005662605,0.0003424506,0.3591167,0.0001060343,0.0002717308,0.0004646009,0.0005085426,0.6274842,0.005602677,0.003510711,0.002477467,0.00005824992],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8517034,0.0007137381,0.1418374,0.0006767875,0.00007847066,0.0003099726,0.001923962,0.00132263,0.001433611],"genre_scores_gemma":[0.9804202,0.00004328356,0.01838948,0.0000313335,0.00003122757,0.00008090336,0.0008507678,0.000009932506,0.0001428556],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005401264,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0659768184388181,"score_gpt":0.3087624777079845,"score_spread":0.2427856592691665,"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."}}