{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002760084,0.0001330264,0.0002007454,0.0001364458,0.0001557599,0.0003585271,0.0003682526,0.00003248052,0.0003002351],"category_scores_gemma":[0.00002742954,0.0001158249,0.0001746082,0.00053658,0.00001092766,0.0002407224,0.0002205639,0.00005225214,0.000149987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003140592,"about_ca_system_score_gemma":0.00004466592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001027554,"about_ca_topic_score_gemma":0.00001166591,"domain_scores_codex":[0.9985644,0.00004936522,0.0002566717,0.0005464767,0.0003183552,0.0002647555],"domain_scores_gemma":[0.9989051,0.0001189669,0.00008172226,0.0007181915,0.00008401251,0.00009196968],"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":[0.00002455146,0.0009124283,0.002392382,0.00004080109,0.001003749,0.0001599277,0.0006685811,0.002510652,0.0110245,0.07234971,0.7716439,0.1372689],"study_design_scores_gemma":[0.001068201,0.00008595334,0.0005640833,0.00004725634,0.0001137865,0.00001279574,0.0001590991,0.4820824,0.06304899,0.0007079401,0.4516443,0.000465193],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008024106,0.0002484033,0.9806868,0.005926237,0.0006376387,0.0002252311,0.0001740893,0.0001265568,0.003950885],"genre_scores_gemma":[0.3326159,0.0000965793,0.6093819,0.01543676,0.0008847092,0.00008329241,0.01051349,0.00006064758,0.03092677],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4795717,"threshold_uncertainty_score":0.4723201,"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."}}