{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002992811,0.0001252388,0.0002414169,0.000361545,0.0001326802,0.00009478274,0.0005411956,0.0000238264,0.0001093311],"category_scores_gemma":[0.000005393381,0.0001029355,0.0001084226,0.00200333,0.00001120021,0.0001051123,0.0005626185,0.00006342998,0.001338364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008723806,"about_ca_system_score_gemma":0.00001645232,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001164624,"about_ca_topic_score_gemma":0.0003575127,"domain_scores_codex":[0.9984241,0.0000903422,0.0002158088,0.0005382435,0.0004788293,0.0002527179],"domain_scores_gemma":[0.9989692,0.0000973656,0.00005063324,0.0007618865,0.00003987687,0.00008106054],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005932595,0.002250814,0.4033328,0.00001669462,0.006174999,0.0004883879,0.06097008,0.4346477,0.00114782,0.0307773,0.0478854,0.01224864],"study_design_scores_gemma":[0.000291988,0.00009523696,0.06776291,0.000002284006,0.00005310066,4.362641e-7,0.000817932,0.9298366,0.0002803543,0.0002012063,0.0005155324,0.0001423964],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6780869,0.000004100818,0.3136934,0.0005619837,0.0001683475,0.0002627434,0.00000157565,0.0003476216,0.006873318],"genre_scores_gemma":[0.9836992,5.015942e-7,0.001439845,0.0001459021,0.00002541581,0.00002691307,0.00000258482,0.000003532227,0.01465612],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4951889,"threshold_uncertainty_score":0.9994392,"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."}}