{"id":"W4317494834","doi":"10.2196/preprints.45767","title":"Using Social Media to Help Understand Patient-Reported Health Outcomes of Post–COVID-19 Condition: Natural Language Processing Approach (Preprint)","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Terminology; Social media; Normalization (sociology); Computer science; Natural language processing; Artificial intelligence; Named-entity recognition; F1 score; Information retrieval; Data science; Task (project management); World Wide Web; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.002027441,0.000738474,0.0002671079,0.002067013,0.0003254166,0.001201482,0.0004403846,0.0005823294,0.003219966],"category_scores_gemma":[0.008404783,0.0001767465,0.0009272405,0.0009439403,0.0003291019,0.001386413,0.0008291735,0.0008729546,0.001529008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008211565,"about_ca_system_score_gemma":0.0008444243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006684965,"about_ca_topic_score_gemma":0.01251367,"domain_scores_codex":[0.999153,0.000347273,0.00009734752,0.0002115279,0.0001379995,0.0000527878],"domain_scores_gemma":[0.9942392,0.004384252,0.0004821755,0.0002413925,0.0005735616,0.00007941853],"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":[0.001501804,0.0008357716,0.1026763,0.002845705,0.000402076,0.002395699,0.005885232,0.01854905,0.04713388,0.007825229,0.06304086,0.7469084],"study_design_scores_gemma":[0.0001703746,0.0007679233,0.1630604,0.000700366,0.0004519415,0.001382807,0.008024557,0.6577452,0.04825546,0.02943271,0.08968469,0.0003235633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4344157,0.001552298,0.426131,0.0101662,0.0006853513,0.002436978,0.1004802,0.0124809,0.01165139],"genre_scores_gemma":[0.5891762,0.0007413797,0.353011,0.0009528904,0.0003234303,0.0013697,0.04996003,0.0003061715,0.00415914],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006684965,"threshold_uncertainty_score":0.01329207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.117922550370415,"score_gpt":0.4041950236947426,"score_spread":0.2862724733243276,"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."}}