{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004635052,0.005709143,0.002457305,0.003225235,0.002495241,0.004018535,0.002730797,0.003414797,0.03966315],"category_scores_gemma":[0.01038132,0.0008612818,0.002643542,0.003028314,0.0006752862,0.004415786,0.006061474,0.003817227,0.07237917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001861441,"about_ca_system_score_gemma":0.003224315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008691994,"about_ca_topic_score_gemma":0.01316626,"domain_scores_codex":[0.9953378,0.001260239,0.0003381704,0.001419266,0.001057924,0.0005865543],"domain_scores_gemma":[0.9955059,0.001046462,0.0002505218,0.001104699,0.001489976,0.000602478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000567727,0.0003258422,0.001496931,0.001084814,0.0001347335,0.0001712383,0.0002097275,0.001046759,0.01186307,0.0007335465,0.9010417,0.08132389],"study_design_scores_gemma":[0.001145692,0.001134055,0.02343041,0.0005198138,0.0002987751,0.00142785,0.001141885,0.07684454,0.04485893,0.01087436,0.8379584,0.0003652969],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.06099931,0.005666263,0.09620082,0.004435454,0.006815074,0.005487014,0.5913903,0.1616662,0.0673397],"genre_scores_gemma":[0.05744357,0.0005743543,0.07572265,0.001441538,0.0008726318,0.003795272,0.8299571,0.005855688,0.02433724],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03966315,"threshold_uncertainty_score":0.1326865,"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."}}