{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01045656,0.0009358934,0.0006129453,0.0006947393,0.0009262834,0.002035349,0.001063753,0.001877501,0.001164537],"category_scores_gemma":[0.06201608,0.0003316477,0.0006836388,0.0008493197,0.001393278,0.00386387,0.001751729,0.003522299,0.0006731453],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008859893,"about_ca_system_score_gemma":0.0005657109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00156025,"about_ca_topic_score_gemma":0.002167169,"domain_scores_codex":[0.9903744,0.007723447,0.0002889351,0.0008638247,0.0005496413,0.0001997157],"domain_scores_gemma":[0.9033193,0.0881763,0.002634271,0.003790821,0.001422043,0.0006572589],"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":[0.00903106,0.004708163,0.3697414,0.002224831,0.0004866389,0.004942074,0.03948435,0.07879404,0.1068475,0.02677683,0.01043586,0.3465273],"study_design_scores_gemma":[0.0004751117,0.002513312,0.05622733,0.0002739235,0.000314359,0.002548164,0.0117186,0.7444654,0.09033698,0.07252058,0.01826554,0.0003406206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9446896,0.0001836519,0.0511731,0.0009413605,0.0000600208,0.0001987266,0.0004431534,0.0004667233,0.001843679],"genre_scores_gemma":[0.9679002,0.00005063544,0.03087457,0.00020126,0.00002838471,0.00008577981,0.0004093243,0.00007819731,0.0003716562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01045656,"threshold_uncertainty_score":0.05530024,"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."}}