{"id":"W4388777264","doi":"10.2196/50150","title":"A Comparison of ChatGPT and Fine-Tuned Open Pre-Trained Transformers (OPT) Against Widely Used Sentiment Analysis Tools: Sentiment Analysis of COVID-19 Survey Data","year":2023,"lang":"en","type":"article","venue":"JMIR Mental Health","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Arthritis and Musculoskeletal and Skin Diseases; National Institutes of Health","keywords":"Sentiment analysis; Computer science; Social media; Context (archaeology); Data science; Sentence; Coronavirus disease 2019 (COVID-19); Artificial intelligence; Data mining; World Wide Web; Medicine","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":[0.005316894,0.001978141,0.0007755687,0.00208539,0.0007234628,0.00138974,0.001598721,0.001214282,0.003234891],"category_scores_gemma":[0.01891799,0.0004417946,0.0009828368,0.0008865898,0.0005860287,0.002694609,0.002007606,0.001891873,0.002679975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001125901,"about_ca_system_score_gemma":0.001397359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005905927,"about_ca_topic_score_gemma":0.009951436,"domain_scores_codex":[0.9970463,0.001184798,0.0002363113,0.0008892293,0.0004389556,0.0002044912],"domain_scores_gemma":[0.9933665,0.004116565,0.000305813,0.0005259257,0.001410937,0.0002742984],"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":[0.004281921,0.001075499,0.03437414,0.002510916,0.0006404236,0.0007200181,0.002167115,0.04227937,0.03688103,0.001847016,0.06410617,0.8091165],"study_design_scores_gemma":[0.0003779518,0.001512285,0.02078464,0.0002939684,0.0002449072,0.0004815272,0.002028418,0.9213839,0.03183194,0.004371306,0.01653077,0.0001584716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5640336,0.003172616,0.3311362,0.001518905,0.00171386,0.001467378,0.01022558,0.07687187,0.009860066],"genre_scores_gemma":[0.7860582,0.0005221931,0.1847815,0.0008958241,0.0001827195,0.0009097069,0.02044017,0.00143156,0.004778157],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005905927,"threshold_uncertainty_score":0.02811879,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1909377796622881,"score_gpt":0.4657761489750528,"score_spread":0.2748383693127647,"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."}}