{"id":"W4410486517","doi":"10.1145/3717867.3717913","title":"Using Semantically Unrelated and Opposite Terms for In-Context Learning: A Case Study in Identifying Political Aversion in Tweets","year":2025,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; American Political Science Association","keywords":"Context (archaeology); Politics; Computer science; Artificial intelligence; Natural language processing; Cognitive psychology; Psychology; Political science; History","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000622209,0.0001047589,0.0002308246,0.0007002085,0.00008349159,0.0001924282,0.0001509119,0.00005664965,0.000005083733],"category_scores_gemma":[0.00006841537,0.00009832512,0.00003977124,0.000716492,0.00001873185,0.0003001793,0.0002733494,0.0001618043,0.000001325307],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008307469,"about_ca_system_score_gemma":0.00003338574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001179093,"about_ca_topic_score_gemma":0.001263623,"domain_scores_codex":[0.9986762,0.000126451,0.0003831115,0.0003931523,0.0001128212,0.0003081972],"domain_scores_gemma":[0.9995106,0.0002302686,0.00003813414,0.0001402096,0.00002622389,0.00005454665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001598363,0.0002269982,0.9778652,0.00002340883,0.00002551238,0.0009943863,0.003277489,0.0003001223,0.0006013653,0.01353195,0.000003734971,0.00313381],"study_design_scores_gemma":[0.00247396,0.00008549495,0.0579751,0.0002235122,0.00002132194,0.00005816359,0.01015866,0.9279206,0.0002636203,0.0006444462,0.000009400838,0.0001657185],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9371264,0.00003255138,0.06193703,0.0002304997,0.00006658393,0.000281714,7.67542e-8,0.00001825161,0.0003068734],"genre_scores_gemma":[0.9962482,0.000001585064,0.003455652,0.0001112207,0.000005115128,0.000005305806,7.341067e-7,0.000003765737,0.0001683694],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9276205,"threshold_uncertainty_score":0.4009582,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06307663292143945,"score_gpt":0.3688733933511384,"score_spread":0.305796760429699,"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."}}