{"id":"W4225832833","doi":"10.2196/32405","title":"Toward Using Twitter for PrEP-Related Interventions: An Automated Natural Language Processing Pipeline for Identifying Gay or Bisexual Men in the United States","year":2022,"lang":"en","type":"article","venue":"JMIR Public Health and Surveillance","topic":"HIV/AIDS Research and Interventions","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of Allergy and Infectious Diseases; National Institutes of Health; Center for AIDS Research, University of Washington; University of Pennsylvania","keywords":"Psychological intervention; Men who have sex with men; Metadata; Pipeline (software); Population; Medicine; Computer science; Social media; Internet privacy; Human immunodeficiency virus (HIV); Psychology; Family medicine; World Wide Web; Environmental health; Nursing; Syphilis","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":[0.001991319,0.0009517151,0.0005053814,0.002903355,0.001036563,0.001234094,0.0008021711,0.0007746145,0.004069019],"category_scores_gemma":[0.00691381,0.0003380738,0.0008898057,0.001244826,0.0003695368,0.002156053,0.00168403,0.0009825082,0.003748872],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009206446,"about_ca_system_score_gemma":0.002071652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01262294,"about_ca_topic_score_gemma":0.01751112,"domain_scores_codex":[0.998854,0.0003474052,0.0001510218,0.0003903132,0.0001694767,0.00008786151],"domain_scores_gemma":[0.9972145,0.001561162,0.0003284203,0.0002064127,0.0005581575,0.0001313642],"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":[0.00157415,0.0008157527,0.1383932,0.002521872,0.0002009487,0.002379243,0.006892357,0.01424851,0.07561515,0.004904817,0.1617981,0.5906559],"study_design_scores_gemma":[0.000204439,0.0005735835,0.0871911,0.0005066568,0.0002083923,0.000803504,0.009191671,0.7175768,0.04666433,0.02157123,0.1153027,0.0002055116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.3908076,0.001678496,0.3301525,0.01321824,0.0006948677,0.005950117,0.1798341,0.06009375,0.01757033],"genre_scores_gemma":[0.3599211,0.0008428472,0.51889,0.00191562,0.0002588029,0.002682295,0.1086797,0.0007081802,0.006101465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01262294,"threshold_uncertainty_score":0.02509898,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.195739898171811,"score_gpt":0.491963296156917,"score_spread":0.296223397985106,"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."}}