{"id":"W4399075343","doi":"10.1038/s41598-024-58944-5","title":"Predicting multi-label emojis, emotions, and sentiments in code-mixed texts using an emojifying sentiments framework","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Institute for Information and Communications Technology Promotion","keywords":"Emoji; Computer science; Sentiment analysis; Natural language processing; Artificial intelligence; Encoder; Code (set theory); Task (project management); Social media; 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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003025402,0.0003121309,0.0003688474,0.0009282352,0.000722713,0.003422367,0.000430093,0.0001522021,0.00004863002],"category_scores_gemma":[0.0001389802,0.000307588,0.0001154016,0.002141107,0.0001457338,0.002099431,0.0005729061,0.0003462226,0.00002658391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001367572,"about_ca_system_score_gemma":0.0001747329,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007241523,"about_ca_topic_score_gemma":0.00003669763,"domain_scores_codex":[0.995203,0.0001835289,0.001060588,0.001935722,0.0009669292,0.0006501863],"domain_scores_gemma":[0.9980258,0.00008769005,0.000337409,0.001156811,0.0001197215,0.0002725917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001276265,0.002476172,0.6712364,0.0005308283,0.0007295837,0.005499732,0.01889386,0.00788736,0.09119824,0.003089324,0.002642234,0.1958035],"study_design_scores_gemma":[0.0002193392,0.00001983734,0.005945868,0.0006782463,0.00004400063,0.0001865227,0.0002904821,0.9869209,0.002169546,0.002665629,0.0005106917,0.000348938],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8304876,0.001163985,0.1583346,0.00009608782,0.009258731,0.0003047291,0.000002651444,0.0002751019,0.00007650789],"genre_scores_gemma":[0.868771,0.00001624513,0.130124,0.00003696262,0.0001053278,0.000009856017,0.00003901099,0.00002993656,0.0008675999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9790335,"threshold_uncertainty_score":0.9999376,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05966954447768665,"score_gpt":0.3387485804253472,"score_spread":0.2790790359476605,"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."}}