{"id":"W7116357590","doi":"10.1016/j.eswa.2025.130869","title":"In-context learning enhanced by multi-perspective sequential retrieval and predictive feedback for few-shot aspect-based sentiment analysis","year":2025,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Université de Montréal","funders":"National Key Research and Development Program of China; Sichuan Province Science and Technology Support Program; National Natural Science Foundation of China; Department of Science and Technology of Sichuan Province; Organization Department of Sichuan Provincial Party Committee; Ministry of Science and Technology of the People's Republic of China; Chinese Academy of Sciences","keywords":"Sentiment analysis; Benchmark (surveying); Parsing; Language model; Labeled data; Training set","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":[0.0002919179,0.0002065033,0.0004067523,0.0004666543,0.000318722,0.0002420824,0.0003236702,0.00007659257,0.000008862986],"category_scores_gemma":[0.00002075134,0.0001861921,0.0001254637,0.001885749,0.00006576887,0.0002298902,0.00006768646,0.0001255638,0.000005355269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002719642,"about_ca_system_score_gemma":0.0001005502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002848233,"about_ca_topic_score_gemma":0.00006656783,"domain_scores_codex":[0.9981878,0.0001047517,0.0003953176,0.0007988526,0.0002434026,0.0002699224],"domain_scores_gemma":[0.9988162,0.0001804331,0.0002197222,0.000430166,0.0002691692,0.00008430477],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00319564,0.006513187,0.04098789,0.0006553903,0.03021311,0.0000179319,0.08837119,0.1962448,0.2987697,0.2950585,0.03096844,0.009004294],"study_design_scores_gemma":[0.003110583,0.0001706913,0.0008148203,0.0001111088,0.0003199194,9.964364e-7,0.009992965,0.9399087,0.03534542,0.00006093574,0.009704005,0.0004598307],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002692452,0.001532844,0.9931575,0.000713598,0.00009302659,0.00127393,0.0000160418,0.00007350206,0.0004470838],"genre_scores_gemma":[0.9882864,0.00001759057,0.008542858,0.0001446311,0.00006155148,0.001305784,0.00005576406,0.00001140568,0.001573964],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.985594,"threshold_uncertainty_score":0.7592695,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01572240722063087,"score_gpt":0.304922359146526,"score_spread":0.2891999519258952,"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."}}