{"id":"W4414681521","doi":"10.1016/j.ins.2025.122704","title":"3WD-DRT: A three-way decision enhanced dynamic routing transformer for cost-sensitive multimodal sentiment analysis","year":2025,"lang":"en","type":"article","venue":"Information Sciences","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University; Université de Montréal","funders":"National Key Research and Development Program of China; Sichuan Province Science and Technology Support Program; National Natural Science Foundation of China; Department of Science and Technology of Sichuan Province; Organization Department of Sichuan Provincial Party Committee; Ministry of Science and Technology of the People's Republic of China; Chinese Academy of Sciences","keywords":"Sentiment analysis; Transformer; Key (lock); Partition (number theory); Routing (electronic design automation); Information fusion","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":[],"consensus_categories":[],"category_scores_codex":[0.001325326,0.0001597273,0.0002765803,0.001068789,0.0006900357,0.0007822391,0.0006522645,0.00005741631,0.00002251954],"category_scores_gemma":[0.00009546035,0.0001300459,0.0002972131,0.003416665,0.0000967259,0.002969029,0.00008232531,0.00006668219,0.00004165467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008711643,"about_ca_system_score_gemma":0.0001144334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005270295,"about_ca_topic_score_gemma":0.0001404237,"domain_scores_codex":[0.9980218,0.00002868783,0.0006690908,0.0003301942,0.0006031625,0.0003470953],"domain_scores_gemma":[0.9987504,0.0003603183,0.000271879,0.000262591,0.0002925045,0.0000623191],"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":[0.00003233143,0.00004894516,0.001624711,0.00001516993,0.0004015636,3.08766e-7,0.005397335,0.0478652,0.001346921,0.01765593,0.0001626646,0.9254489],"study_design_scores_gemma":[0.0004637652,0.00003638133,0.007159466,0.00003616429,0.00009295284,3.777114e-7,0.0008045511,0.9817512,0.008311396,0.000583075,0.0006009226,0.000159766],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05712282,0.00001690588,0.9389042,0.0006506212,0.0003522044,0.0004229927,0.000007903887,0.00006744576,0.002454858],"genre_scores_gemma":[0.9324053,0.000007721748,0.06699293,0.0004332321,0.00001002388,0.0000451964,0.00002202495,0.000001527132,0.00008207257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.933886,"threshold_uncertainty_score":0.754315,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0150989243965553,"score_gpt":0.3201133537543306,"score_spread":0.3050144293577753,"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."}}