{"id":"W4409555240","doi":"10.1177/30504554251326853","title":"Improving Sentiment Classification Using 0-Shot Generated Labels for Custom Transformer Embeddings","year":2025,"lang":"en","type":"article","venue":"The European Journal on Artificial Intelligence","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Transformer; Computer science; Shot (pellet); Artificial intelligence; Sentiment analysis; Single shot; Pattern recognition (psychology); Natural language processing; Engineering; Materials science; Electrical engineering; Physics; Optics; Voltage","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001007676,0.001462559,0.0006479977,0.0006515398,0.000369445,0.0009740127,0.001035471,0.0008826164,0.003282027],"category_scores_gemma":[0.004815028,0.0003415377,0.0006608933,0.0003949164,0.0005480346,0.002980636,0.001253772,0.001738081,0.002738327],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008029871,"about_ca_system_score_gemma":0.0006049396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001886808,"about_ca_topic_score_gemma":0.004680323,"domain_scores_codex":[0.9995524,0.0001215739,0.00002277334,0.0001467764,0.00009651308,0.00005991856],"domain_scores_gemma":[0.9987119,0.0005709212,0.00008921268,0.0002741042,0.0002932836,0.00006061099],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001173645,0.0007121133,0.01426656,0.0003603886,0.0001294523,0.000263099,0.0005434943,0.09885295,0.05573133,0.01058216,0.02034849,0.7970362],"study_design_scores_gemma":[0.00003746252,0.0002097441,0.001090295,0.0000279315,0.00003738478,0.00007833292,0.000111935,0.9688465,0.01586722,0.009605113,0.004064914,0.00002307831],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2136581,0.0007384615,0.7622802,0.0007772172,0.0004521632,0.0002464153,0.001149443,0.01238603,0.008312039],"genre_scores_gemma":[0.8241296,0.0002055699,0.1627636,0.0004354199,0.0001295379,0.0001781832,0.003538899,0.0006346973,0.007984359],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003282027,"threshold_uncertainty_score":0.01097953,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1229090906466905,"score_gpt":0.3467678807937661,"score_spread":0.2238587901470755,"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."}}