{"id":"W4409787628","doi":"10.61091/jcmcc127a-398","title":"Dynamic analysis of classroom engagement sentiment based on multilevel feature extraction and Transformer CNN-LSTM integrated model: personalized behavior prediction for non-English learners in a cross-modal adversarial learning framework","year":2025,"lang":"en","type":"article","venue":"Journal of Combinatorial Mathematics and Combinatorial Computing","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Modal; Transformer; Artificial intelligence; Feature extraction; Sentiment analysis; Adversarial system; Multimodality; Feature learning; Deep learning; Natural language processing; Speech recognition; Engineering; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002125507,0.0002953754,0.0008697092,0.0009102747,0.0002877096,0.000281235,0.0003257169,0.0003001846,0.000001390357],"category_scores_gemma":[0.0007600909,0.0002757394,0.0003364725,0.0008983227,0.00007911416,0.0002621893,0.00007027949,0.001195628,6.071446e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002165228,"about_ca_system_score_gemma":0.0002606722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008571063,"about_ca_topic_score_gemma":8.642333e-7,"domain_scores_codex":[0.9975738,0.0001733746,0.001005309,0.0003563848,0.0005968457,0.0002942867],"domain_scores_gemma":[0.9971424,0.001048648,0.0008605654,0.0001975894,0.0006458858,0.0001048748],"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":[0.001931501,0.004604294,0.01322003,0.0009377197,0.001988067,0.00002569208,0.01538819,0.6328648,0.002639025,0.3129548,0.00005049003,0.01339536],"study_design_scores_gemma":[0.006317774,0.0007176337,0.001146896,0.0006261191,0.0007691265,0.000001560972,0.0006992703,0.9680158,0.0001524097,0.02130344,0.00004707983,0.000202845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4692542,0.00002774905,0.5274087,0.0001297861,0.002819056,0.0002957769,0.000006105402,0.00002604125,0.00003261461],"genre_scores_gemma":[0.9469836,0.00001927867,0.05279456,0.0000152766,0.0001281971,0.000007158962,0.00001054394,0.00001738566,0.00002393854],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4777295,"threshold_uncertainty_score":0.9999695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01051697465482081,"score_gpt":0.3087622635443383,"score_spread":0.2982452888895175,"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."}}