{"id":"W4414187888","doi":"10.1016/j.ins.2025.122684","title":"SEAD-MGFE-Net: Schrödinger equation-based adaptive dropout multi-granular feature enhancement network for conversational aspect-based sentiment quadruple analysis","year":2025,"lang":"en","type":"article","venue":"Information Sciences","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; McGill University","funders":"Science and Technology Service Network Plan; National Key Research and Development Program of China; Sichuan Province Science and Technology Support Program; Chengdu Science and Technology Bureau; Organization Department of Sichuan Provincial Party Committee; Ministry of Science and Technology of the People's Republic of China; Chinese Academy of Sciences; National Natural Science Foundation of China","keywords":"Dropout (neural networks); Sentiment analysis; Feature (linguistics); Benchmark (surveying); Regularization (linguistics); Adjacency list; Feature extraction; Syntax; Sentence","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":[0.001602433,0.0002049835,0.0002861724,0.0009495489,0.0008615323,0.0008143215,0.0007382482,0.00007568691,0.0001261564],"category_scores_gemma":[0.00008301951,0.0001809791,0.0003068436,0.003787622,0.0001372872,0.001614989,0.00007569553,0.00008679742,0.00005573968],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001524256,"about_ca_system_score_gemma":0.0004972176,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006450624,"about_ca_topic_score_gemma":0.00003625113,"domain_scores_codex":[0.9976309,0.00008146126,0.0005871687,0.0004006843,0.0009151156,0.0003846599],"domain_scores_gemma":[0.9982495,0.000377189,0.0004728448,0.0003362132,0.0004844596,0.00007980508],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004060632,0.0001549173,0.02066675,0.00003482535,0.0004275636,3.558141e-7,0.001043543,0.9100315,0.0001050201,0.05336928,0.008375094,0.00575054],"study_design_scores_gemma":[0.0008292701,0.00008139836,0.002472258,0.00003402643,0.0001381124,5.23522e-8,0.000313591,0.9879615,0.002347052,0.0002538838,0.005362299,0.0002065465],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00215418,0.00009296001,0.9930601,0.002928894,0.0004794502,0.0004593565,0.00001425674,0.00007900026,0.000731853],"genre_scores_gemma":[0.6976402,0.000002652891,0.299446,0.002179701,0.00005047163,0.0001157181,0.0002447577,0.000002752072,0.0003177926],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.695486,"threshold_uncertainty_score":0.7852521,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03369677835212775,"score_gpt":0.3038836580473439,"score_spread":0.2701868796952162,"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."}}