{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001651163,0.0001473859,0.0004379885,0.00008472889,0.0000652985,0.00001664605,0.00025447,0.0001159237,0.00001950786],"category_scores_gemma":[0.004889744,0.00009609578,0.00003804274,0.0003412816,0.0002451407,0.0004117841,0.0002686656,0.0003676722,0.000002303342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008150005,"about_ca_system_score_gemma":0.0009156444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003532042,"about_ca_topic_score_gemma":0.0002744213,"domain_scores_codex":[0.9977581,0.0001840373,0.000860288,0.0001355905,0.000826416,0.0002356029],"domain_scores_gemma":[0.9975917,0.001261348,0.0003290014,0.0004285617,0.0001424133,0.0002470035],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003793463,0.0001685169,0.364821,0.0008794989,0.0001023551,0.00001961791,0.6275545,0.00001385291,0.000008993971,0.00003034053,0.000740906,0.005281107],"study_design_scores_gemma":[0.008447749,0.000158376,0.243243,0.0003082975,0.0001069086,0.00005046527,0.741927,0.003377032,0.00001624402,0.0000539108,0.002124062,0.0001869008],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9975773,0.000108276,0.0007321479,0.0003829518,0.00007136476,0.000865414,0.000166844,0.00003542237,0.00006031795],"genre_scores_gemma":[0.9961634,0.00001894132,0.001264773,0.001945551,0.0001326994,0.000117047,0.0003323342,0.00001215696,0.00001310668],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.121578,"threshold_uncertainty_score":0.5853834,"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."}}