{"id":"W4408612519","doi":"10.2196/60528","title":"Natural Language Processing and Machine Learning Techniques for Analyzing Conversations About Nutritional Yeasts in the United States and France: Retrospective Social Media Listening Study","year":2025,"lang":"en","type":"article","venue":"JMIR Infodemiology","topic":"Social Media in Health Education","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; Natural (archaeology); Social media; Natural language processing; Artificial intelligence; World Wide Web; History; Archaeology","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":[0.002456971,0.0003812455,0.0003191041,0.004612426,0.0009188627,0.001572299,0.0003571082,0.0005950882,0.00130479],"category_scores_gemma":[0.008354154,0.0001730999,0.0004964207,0.00274093,0.0004803396,0.0009540107,0.0008660702,0.0005190701,0.0006203461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001212201,"about_ca_system_score_gemma":0.000663339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03086013,"about_ca_topic_score_gemma":0.03458628,"domain_scores_codex":[0.9981654,0.0009428118,0.0001371945,0.0002675961,0.0003081731,0.0001788197],"domain_scores_gemma":[0.9915137,0.004655196,0.001259631,0.0003333099,0.001967257,0.0002708775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003747435,0.0006414918,0.8194332,0.0004957464,0.0002162799,0.001741871,0.06551962,0.0008522287,0.009823211,0.0009947936,0.006407639,0.09349917],"study_design_scores_gemma":[0.00001591282,0.0002799857,0.9272104,0.0001165943,0.0000792001,0.0005887385,0.04946029,0.006783576,0.001788546,0.0002958173,0.01330506,0.00007582927],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9928647,0.0002079135,0.001829216,0.0003032969,0.00001411439,0.0001338735,0.002882234,0.0000561373,0.001708442],"genre_scores_gemma":[0.9875757,0.000310048,0.004807159,0.0002598961,0.00008942096,0.0004583685,0.00483879,0.00002990683,0.001630699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03086013,"threshold_uncertainty_score":0.06136101,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04008932125801526,"score_gpt":0.4221914162729474,"score_spread":0.3821020950149321,"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."}}