{"id":"W7106612763","doi":"10.1016/j.procs.2025.10.207","title":"Multi-label classification of evolving psychosocial concerns using prompt-based large language models","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Mental Health via Writing","field":"Psychology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique; Université du Québec à Rimouski","funders":"","keywords":"Subcategory; Task (project management); Language model; Psychosocial; Language understanding","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001704086,0.001330264,0.0003879598,0.001477443,0.0004597122,0.001434775,0.001068514,0.001256548,0.005186041],"category_scores_gemma":[0.01191561,0.0002082636,0.000717489,0.0007831044,0.0003865153,0.002621877,0.001775282,0.002114133,0.003811069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009335908,"about_ca_system_score_gemma":0.001453805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001705059,"about_ca_topic_score_gemma":0.004698051,"domain_scores_codex":[0.9987219,0.0005469228,0.00009356835,0.0003472018,0.0002242985,0.0000660514],"domain_scores_gemma":[0.9917665,0.004999731,0.0006872074,0.0006948937,0.00141149,0.0004401125],"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":[0.001269132,0.0009205231,0.05868764,0.001419018,0.00009801576,0.001770288,0.006217469,0.01407491,0.03780818,0.006515002,0.08447417,0.7867457],"study_design_scores_gemma":[0.0002355006,0.001068664,0.04041801,0.0005485481,0.0001792727,0.002071436,0.009081562,0.7053279,0.05420944,0.07337244,0.1131816,0.0003056398],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4413857,0.00184682,0.4609885,0.005093983,0.001473346,0.001381707,0.02778393,0.04503674,0.01500945],"genre_scores_gemma":[0.7300889,0.0003888746,0.2362991,0.001048259,0.0002414267,0.0007017637,0.0210795,0.0007036475,0.009448623],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005186041,"threshold_uncertainty_score":0.01734906,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1109102422659512,"score_gpt":0.4368632485065511,"score_spread":0.3259530062405999,"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."}}