{"id":"W4389518435","doi":"10.18653/v1/2023.banglalp-1.43","title":"Z-Index at BLP-2023 Task 2: A Comparative Study on Sentiment Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Lexical analysis; Computer science; Task (project management); Index (typography); Artificial intelligence; Natural language processing; Sentiment analysis; Class (philosophy); Machine learning; World Wide Web; Engineering","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":[0.00618304,0.002424696,0.001477771,0.002763414,0.001258623,0.002463587,0.001427325,0.001815159,0.006039879],"category_scores_gemma":[0.01403414,0.0003270042,0.001187261,0.002040511,0.0005176073,0.003956749,0.00258564,0.001620994,0.007591422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009767188,"about_ca_system_score_gemma":0.0008869299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005861858,"about_ca_topic_score_gemma":0.007402394,"domain_scores_codex":[0.994484,0.002191207,0.0004259657,0.001130261,0.001308828,0.0004597686],"domain_scores_gemma":[0.9912538,0.004471263,0.0003953094,0.001322876,0.00186188,0.0006950334],"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":[0.008258714,0.00391013,0.06263602,0.003826136,0.001373346,0.001040223,0.003013181,0.01268682,0.08193194,0.001382569,0.2057748,0.6141663],"study_design_scores_gemma":[0.001437596,0.009351524,0.3598074,0.0004889249,0.001086947,0.002625901,0.007468978,0.3807714,0.08123435,0.006154813,0.1489085,0.0006636942],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8707215,0.007955247,0.04075206,0.001724254,0.002056943,0.001146873,0.02795827,0.01742672,0.03025813],"genre_scores_gemma":[0.8437766,0.001178563,0.03984392,0.0005966388,0.0007008404,0.0008468704,0.09768775,0.002342758,0.01302614],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00618304,"threshold_uncertainty_score":0.03269947,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06926382760000373,"score_gpt":0.3334456753192457,"score_spread":0.264181847719242,"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."}}