{"id":"W3177040000","doi":"10.2196/27670","title":"Social Media Monitoring of the COVID-19 Pandemic and Influenza Epidemic With Adaptation for Informal Language in Arabic Twitter Data: Qualitative Study","year":2021,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Deanship of Scientific Research, King Saud University; King Saud University; University of Leeds","keywords":"Computer science; Social media; Natural language processing; Artificial intelligence; Naive Bayes classifier; Terminology; Sentiment analysis; Support vector machine; Information retrieval; Data science; World Wide Web; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003478265,0.0002971508,0.0002670005,0.001377146,0.002286816,0.001400596,0.0005429938,0.000572879,0.002614593],"category_scores_gemma":[0.01129041,0.0002349565,0.0002042775,0.001219109,0.001745521,0.002337616,0.002134693,0.0007833309,0.0003109127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002306442,"about_ca_system_score_gemma":0.001072017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01003243,"about_ca_topic_score_gemma":0.01556907,"domain_scores_codex":[0.9982228,0.001108935,0.00007639927,0.000161442,0.0002007613,0.0002297405],"domain_scores_gemma":[0.9925553,0.004852897,0.001088502,0.0001733917,0.00100201,0.0003277664],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00008343771,0.0000807295,0.1172584,0.0004586864,0.00001888002,0.00171461,0.8586757,0.00008862666,0.001953414,0.001329783,0.001894031,0.01644365],"study_design_scores_gemma":[0.000002928425,0.00004381381,0.04417256,0.0001561347,0.00001003424,0.000266887,0.9492095,0.0003828039,0.0003794591,0.0002245254,0.005132003,0.0000193416],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957046,0.0001587621,0.0004557526,0.00100548,0.00001349162,0.00008967807,0.0003323427,0.00000523923,0.002234574],"genre_scores_gemma":[0.9976225,0.0002235021,0.0004581325,0.0003175145,0.000009716648,0.0001931368,0.000135385,0.00001079291,0.001029242],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01003243,"threshold_uncertainty_score":0.01994812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1639337992724459,"score_gpt":0.4616320856267709,"score_spread":0.297698286354325,"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."}}