{"id":"W4391074521","doi":"10.1016/j.engappai.2024.107907","title":"AGCVT-prompt for sentiment classification: Automatically generating chain of thought and verbalizer in prompt learning","year":2024,"lang":"en","type":"article","venue":"Engineering Applications of Artificial Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Key Science and Technology Program of Shaanxi Province; Department of Science and Technology of Sichuan Province; National Natural Science Foundation of China","keywords":"Computer science; Interpretability; Artificial intelligence; Template; Transparency (behavior); Deep learning; Sentiment analysis; Machine learning; Natural language processing; Computer security","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":[0.0005090358,0.0001032896,0.000175901,0.0002476689,0.00005217841,0.00009111978,0.0002579759,0.00004321081,0.000007518825],"category_scores_gemma":[0.0000596436,0.0001062143,0.00006043481,0.0007077794,0.00003361583,0.0001401991,0.00007013638,0.00009546246,0.000004868428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002457831,"about_ca_system_score_gemma":0.00003155491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006753834,"about_ca_topic_score_gemma":0.000001473938,"domain_scores_codex":[0.9988107,0.00001749332,0.0005547227,0.0003120946,0.0001585853,0.0001463813],"domain_scores_gemma":[0.9993288,0.0002278886,0.00009179985,0.0002372431,0.00007787342,0.00003639649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002252543,0.00007378002,0.00009575163,0.0002810823,0.00004248088,4.614665e-7,0.001320986,0.1035267,0.06980186,0.6407194,0.00001797927,0.1841172],"study_design_scores_gemma":[0.00001368851,0.00002621915,0.0001191158,0.0001129092,0.00000985376,9.397453e-7,0.0001247788,0.9515442,0.04609471,0.001161438,0.0006981978,0.00009396592],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01649892,0.0006293895,0.9820184,0.000308549,0.00007141812,0.0003432294,0.000001869746,0.00008897339,0.00003922359],"genre_scores_gemma":[0.749157,0.00002859392,0.2504836,0.00000401335,0.00005305058,0.0002053985,0.000006858579,0.000009533832,0.00005191603],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8480175,"threshold_uncertainty_score":0.4331294,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02761439038441367,"score_gpt":0.2969081063464841,"score_spread":0.2692937159620705,"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."}}