{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001421921,0.00007551847,0.0001789168,0.0002040625,0.0008394934,0.00004375209,0.0000926117,0.0001181532,0.000002673142],"category_scores_gemma":[0.00408826,0.0000670571,0.00001715819,0.0005278058,0.0003547574,0.0001068244,0.00002834303,0.0003836486,1.014195e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001280674,"about_ca_system_score_gemma":0.0001329959,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002759935,"about_ca_topic_score_gemma":0.003407977,"domain_scores_codex":[0.998749,0.0005512603,0.0002227211,0.000169253,0.0001019439,0.0002058317],"domain_scores_gemma":[0.9963333,0.003328486,0.0001293488,0.00003482388,0.0001490984,0.00002491547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001604485,0.0000255518,0.6936611,0.0000294958,0.00000466016,2.981367e-7,0.2995756,0.000001321688,0.00000727629,0.001901267,0.00002148423,0.004755874],"study_design_scores_gemma":[0.0003436609,0.00003229639,0.878017,0.00004228722,0.00001284189,2.889363e-7,0.1173919,0.00101629,0.000001706348,0.002284057,0.000791697,0.00006601137],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9926367,0.001010344,0.0001447931,0.004512725,0.0002121184,0.00135252,0.000007560773,0.00005730448,0.00006590994],"genre_scores_gemma":[0.9973341,0.0001069628,0.0005831687,0.0003792471,0.0002707557,0.001252481,0.0000597198,0.000004309343,0.000009276367],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1843559,"threshold_uncertainty_score":0.6456789,"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."}}