{"id":"W4286497605","doi":"10.2196/37350","title":"Integrating Natural Language Processing and Interpretive Thematic Analyses to Gain Human-Centered Design Insights on HIV Mobile Health: Proof-of-Concept Analysis","year":2022,"lang":"en","type":"article","venue":"JMIR Human Factors","topic":"Mobile Health and mHealth Applications","field":"Health Professions","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute on Drug Abuse","keywords":"Thematic analysis; mHealth; Latent Dirichlet allocation; Sentiment analysis; Social media; Psychological intervention; Computer science; Psychology; World Wide Web; Qualitative research; Topic model; Artificial intelligence; Sociology","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":[0.05364985,0.001622606,0.000766643,0.002820757,0.001842243,0.004864423,0.002272998,0.001150751,0.009444422],"category_scores_gemma":[0.07041367,0.0006793037,0.002390192,0.0016312,0.004753463,0.004292714,0.004409045,0.002264365,0.001181839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003787406,"about_ca_system_score_gemma":0.006990894,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00157088,"about_ca_topic_score_gemma":0.002549145,"domain_scores_codex":[0.970402,0.02192243,0.001076988,0.001925926,0.004104154,0.0005685404],"domain_scores_gemma":[0.8871181,0.09489474,0.002750046,0.005087721,0.009566571,0.0005829158],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0009032307,0.002130445,0.008195217,0.0169,0.0003816994,0.001331102,0.1787942,0.01915705,0.0382494,0.1891159,0.01451205,0.5303297],"study_design_scores_gemma":[0.002574666,0.003873664,0.009752172,0.01012421,0.0008489448,0.001194096,0.1145374,0.1595863,0.08736318,0.3205616,0.2890188,0.0005649502],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06203067,0.000398488,0.9049649,0.00196528,0.0001852078,0.01712238,0.002259805,0.0006724479,0.01040089],"genre_scores_gemma":[0.07452292,0.000183581,0.9111263,0.0003113664,0.00002765068,0.01220218,0.0004420219,0.0001423751,0.001041547],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05364985,"threshold_uncertainty_score":0.283731,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1132890649523768,"score_gpt":0.491038766325696,"score_spread":0.3777497013733192,"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."}}