{"id":"W3212697960","doi":"10.18653/v1/2021.findings-emnlp.278","title":"SentNoB: A Dataset for Analysing Sentiment on Noisy Bangla Texts","year":2021,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Bengali; Computer science; Benchmark (surveying); Artificial intelligence; Sentiment analysis; Natural language processing; Social media; Polarity (international relations); Artificial neural network; World Wide Web","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":[0.0006538492,0.00128031,0.0006301954,0.003547452,0.001007394,0.001065618,0.0009704193,0.001114662,0.008014943],"category_scores_gemma":[0.003922466,0.0002318831,0.0004749369,0.002893071,0.0003555896,0.001163641,0.001129669,0.0007436894,0.009852801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008396283,"about_ca_system_score_gemma":0.0007886795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005966264,"about_ca_topic_score_gemma":0.01605825,"domain_scores_codex":[0.9988789,0.0002671046,0.0002040392,0.0002107041,0.0003351477,0.0001040056],"domain_scores_gemma":[0.9980361,0.0005423102,0.0002749384,0.0002769215,0.0006734163,0.0001963425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009519132,0.0006051409,0.01829165,0.003036678,0.0001661852,0.0009985944,0.001084463,0.001812001,0.01894313,0.00262497,0.8323027,0.1191826],"study_design_scores_gemma":[0.0003124182,0.0003176057,0.08507221,0.0005102853,0.0001135676,0.001091794,0.002116688,0.02484567,0.01640337,0.003450066,0.8655881,0.0001782419],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0716285,0.001371807,0.008106934,0.000826641,0.0006023159,0.0008401325,0.8926316,0.006627565,0.0173645],"genre_scores_gemma":[0.04151781,0.0003374789,0.01452934,0.0002041085,0.0001130173,0.0008164678,0.937367,0.0002909961,0.004823645],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.008014943,"threshold_uncertainty_score":0.02681267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03168555132132317,"score_gpt":0.3080371838795893,"score_spread":0.2763516325582662,"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."}}