{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006102235,0.0007405017,0.0003369499,0.001198103,0.0003179083,0.0005831617,0.000403903,0.0005628848,0.0007425383],"category_scores_gemma":[0.002416855,0.000161276,0.0006139931,0.000701952,0.0003023968,0.0009439425,0.000527303,0.000773672,0.0003629831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000527052,"about_ca_system_score_gemma":0.0005992554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003760201,"about_ca_topic_score_gemma":0.005330438,"domain_scores_codex":[0.9996473,0.00008478313,0.00003435795,0.0001141223,0.00006920405,0.00005028018],"domain_scores_gemma":[0.9986223,0.0009416916,0.000146316,0.0000753624,0.0001711527,0.00004312488],"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":[0.001264319,0.001245882,0.06038988,0.000632089,0.0002129679,0.001579124,0.001682627,0.06531126,0.03662759,0.002199292,0.01126977,0.8175853],"study_design_scores_gemma":[0.00003261585,0.0002845642,0.0187848,0.00003321157,0.0001062425,0.0003004454,0.0006981125,0.9650139,0.009962882,0.002732391,0.002013567,0.00003733233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8356952,0.001062943,0.1552517,0.0008129152,0.0001947949,0.000256599,0.002367766,0.001861697,0.002496439],"genre_scores_gemma":[0.9519103,0.0002668086,0.04318555,0.000119642,0.00007544202,0.0001112482,0.00271845,0.00003118953,0.001581464],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003760201,"threshold_uncertainty_score":0.007476628,"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."}}