{"id":"W4389518355","doi":"10.18653/v1/2023.banglalp-1.48","title":"BLP-2023 Task 2: Sentiment Analysis","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Scripting language; Task (project management); Domain (mathematical analysis); Sentiment analysis; Artificial intelligence; Natural language processing; Data science; Machine learning; Programming language; Systems 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":[0.0002084413,0.00005634647,0.00009411815,0.0002448412,0.00004926691,0.00008369539,0.0004471291,0.00002074812,0.0001384458],"category_scores_gemma":[0.000007826953,0.00004874227,0.00008962838,0.001926445,0.000005786504,0.0001235016,0.0002974954,0.00003059181,0.001042335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001682982,"about_ca_system_score_gemma":0.00001433637,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007300735,"about_ca_topic_score_gemma":0.00003265225,"domain_scores_codex":[0.999172,0.00001844434,0.0001239708,0.0002781208,0.0002183829,0.0001891072],"domain_scores_gemma":[0.999342,0.00003049189,0.00002030391,0.0005309723,0.00002139335,0.0000548862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002910384,0.0001495378,0.02894497,0.00003248482,0.002098185,0.0002606527,0.003337126,0.1238934,0.004175317,0.4443939,0.1057075,0.287004],"study_design_scores_gemma":[0.00005223081,0.000004524756,0.003040568,0.000001044057,0.00002550573,5.03205e-7,0.00001994959,0.9890751,0.0004263977,0.001538918,0.005738409,0.00007680997],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02218956,0.00001030283,0.965251,0.001958335,0.0001945333,0.00004145717,6.292537e-7,0.0004792364,0.009874934],"genre_scores_gemma":[0.9032619,0.000006350127,0.0580667,0.0004752919,0.00005910179,0.000009955663,0.000004123367,0.000004508329,0.03811204],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9071843,"threshold_uncertainty_score":0.9997355,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02410934100984339,"score_gpt":0.2656342560470115,"score_spread":0.2415249150371681,"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."}}