{"id":"W4281291858","doi":"10.2196/37840","title":"Extracting Multiple Worries From Breast Cancer Patient Blogs Using Multilabel Classification With the Natural Language Processing Model Bidirectional Encoder Representations From Transformers: Infodemiology Study of Blogs","year":2022,"lang":"en","type":"article","venue":"JMIR Cancer","topic":"Mental Health via Writing","field":"Psychology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Breast cancer; Computer science; Encoder; Social media; Classifier (UML); Concordance; Artificial intelligence; Worry; Psychology; Machine learning; Natural language processing; Medicine; Cancer; World Wide Web; Psychiatry; Internal medicine","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":[0.0001849551,0.0002027349,0.0002780023,0.0001041114,0.0007527354,0.00002131587,0.0001886781,0.00007052065,0.0008136687],"category_scores_gemma":[0.00001448895,0.0001610968,0.00004950507,0.000363421,0.0001203518,0.0002264096,0.00006242952,0.0006043539,0.000001291242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004648992,"about_ca_system_score_gemma":0.0002514979,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05946586,"about_ca_topic_score_gemma":0.01161522,"domain_scores_codex":[0.9978307,0.0003519499,0.0005365512,0.000533017,0.0004009607,0.000346759],"domain_scores_gemma":[0.998565,0.0004131732,0.0005807786,0.0002552279,0.0001284207,0.00005735354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001793652,0.001275888,0.5423726,0.00005248517,0.0003123974,0.00001022312,0.2826914,0.04290701,0.02163755,0.0000123418,0.00026233,0.106672],"study_design_scores_gemma":[0.002639816,0.0001164047,0.287892,0.0001060103,0.0001445244,0.00001836646,0.3432435,0.3652253,0.0001729741,0.00001160563,0.0001337477,0.0002957713],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936336,0.002494069,0.0003286159,0.0005779853,0.0004349661,0.001285326,0.001042504,0.00006071411,0.0001422134],"genre_scores_gemma":[0.9952066,0.00001012307,0.0008088513,0.0003883175,0.0001632539,0.003187364,0.00009976893,0.00004110906,0.00009459513],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3223182,"threshold_uncertainty_score":0.9467973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07196328323403142,"score_gpt":0.415168804549865,"score_spread":0.3432055213158336,"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."}}