{"id":"W7117138955","doi":"10.1016/j.engappai.2025.113584","title":"A method for extracting emotion–cause pairs based on bidirectional machine reading comprehension","year":2025,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Hebei Province Science and Technology Support Program; Hebei Provincial Department of Bureau of Science and Technology; Guangdong University of Foreign Studies; Ministry of Education of the People's Republic of China","keywords":"Benchmark (surveying); Graph; Filter (signal processing); Task (project management); Attention network; Exploit; Comprehension","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":[0.0004782354,0.0001131296,0.0001558815,0.0004326898,0.0001632984,0.00006136507,0.0003401081,0.00004447856,0.00001092272],"category_scores_gemma":[0.0001019185,0.0001211686,0.0001107803,0.0009496633,0.00001368599,0.0000986473,0.00004423583,0.00009959735,0.000007646304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004028744,"about_ca_system_score_gemma":0.00003205776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001561676,"about_ca_topic_score_gemma":0.00000118955,"domain_scores_codex":[0.9989605,0.00002270254,0.0003933145,0.0003233956,0.0001553228,0.0001447417],"domain_scores_gemma":[0.998563,0.0007747558,0.0001145643,0.000369388,0.0001423272,0.00003595911],"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":[0.000008988781,0.00011818,0.00007196257,0.00003701248,0.00003438039,1.430775e-7,0.00006839858,0.5328093,0.01075823,0.2547499,0.00006231236,0.2012812],"study_design_scores_gemma":[0.00002115351,0.0000218476,0.00007687266,0.00006541681,0.00001498116,3.89992e-7,0.00003187329,0.93119,0.06485602,0.001677116,0.001953333,0.00009101578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004224885,0.00004453375,0.9983318,0.0004938176,0.0001584673,0.0002624059,0.000003540718,0.0001352733,0.0001476092],"genre_scores_gemma":[0.3699926,0.000004135207,0.6297122,0.00004687236,0.00004673272,0.0001243639,0.00001215237,0.000007176691,0.00005377849],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3983807,"threshold_uncertainty_score":0.4941113,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03792664972755048,"score_gpt":0.3372674994288623,"score_spread":0.2993408497013118,"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."}}