{"id":"W4393957106","doi":"10.2196/51332","title":"Differing Content and Language Based on Poster-Patient Relationships on the Chinese Social Media Platform Weibo: Text Classification, Sentiment Analysis, and Topic Modeling of Posts on Breast Cancer","year":2024,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Mental Health via Writing","field":"Psychology","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Social media; Computer science; Sentiment analysis; Content (measure theory); Natural language processing; Information retrieval; World Wide Web; Artificial intelligence; Mathematics","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":[0.0001806243,0.0001477893,0.0001928179,0.0001764695,0.0001733124,0.00003225003,0.00005837858,0.00007563727,0.0002962619],"category_scores_gemma":[0.00001153544,0.0001005682,0.00005801668,0.0002721451,0.00003941929,0.00004029741,0.00002276428,0.0002667849,0.000006251379],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002431359,"about_ca_system_score_gemma":0.00003014974,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006518447,"about_ca_topic_score_gemma":0.0007455769,"domain_scores_codex":[0.9988633,0.00008935711,0.0003057559,0.0003092917,0.0002467446,0.0001855514],"domain_scores_gemma":[0.9993138,0.0003085838,0.0001010387,0.0001776055,0.00003524019,0.00006372703],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001862871,0.0007107364,0.6270581,0.0008657759,0.00119908,0.00003394593,0.1394814,0.001604316,0.003631848,0.01001805,0.0006938811,0.2128399],"study_design_scores_gemma":[0.0004719092,0.00008443603,0.9336118,0.0003424808,0.0001020655,0.000002065932,0.003575846,0.06153363,0.00008364208,0.00003477759,0.00002615681,0.0001312269],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931227,0.0006193208,0.00002542974,0.004401844,0.000331634,0.0004474655,0.0002210879,0.00002872494,0.0008018115],"genre_scores_gemma":[0.9986995,0.00001600841,0.000006987233,0.0006233613,0.0001681662,0.0003480049,0.00002546441,0.00001882819,0.00009363391],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3065536,"threshold_uncertainty_score":0.4101053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07644993146804749,"score_gpt":0.3725930366192592,"score_spread":0.2961431051512118,"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."}}