{"id":"W4220661484","doi":"10.1145/3519304","title":"Deep Hierarchical Attention Active Learning for Mental Disorder Unlabeled Data in AIoMT","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Sensor Networks","topic":"Mental Health via Writing","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Sentence; Lexicon; Artificial intelligence; Natural language processing; Mental lexicon; Representation (politics); Segmentation; Set (abstract data type); Machine learning; Mental health; Word (group theory); Semantics (computer science); Psychology; Linguistics; Psychiatry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005630407,0.0002004206,0.0002507368,0.0002174092,0.0009847794,0.00002127503,0.0005273736,0.0001224529,0.001868535],"category_scores_gemma":[0.00003101778,0.000239573,0.00008950959,0.0004840932,0.00005615027,0.0001384509,0.00005689718,0.001411991,0.00003428367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002735142,"about_ca_system_score_gemma":0.0000216237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002110377,"about_ca_topic_score_gemma":0.0003380917,"domain_scores_codex":[0.9972982,0.0006421069,0.0004478196,0.0007167935,0.0002645302,0.0006305333],"domain_scores_gemma":[0.9981197,0.0008240512,0.0001248256,0.0008014507,0.00002027723,0.0001097046],"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":[0.003636679,0.001923875,0.005154025,0.00004459255,0.0002313569,0.00003889494,0.003129242,0.1836015,0.0001705298,0.0002505833,0.0004688933,0.8013498],"study_design_scores_gemma":[0.01502168,0.002281995,0.03407697,0.0001098684,0.0001966018,0.000221707,0.04531036,0.8614342,0.00003061842,0.0005193922,0.03960641,0.001190256],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5360476,0.0003048081,0.4540266,0.003017528,0.002737851,0.002433827,0.0002551879,0.0002311703,0.0009453928],"genre_scores_gemma":[0.9940828,0.00003241518,0.002520434,0.0004647522,0.0001373981,0.0006707794,0.000880515,0.00006759104,0.001143282],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8001596,"threshold_uncertainty_score":0.9990439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04758898485458482,"score_gpt":0.36285538119022,"score_spread":0.3152663963356351,"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."}}