{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005379669,0.001515516,0.0003890253,0.001176422,0.0003971766,0.0006262509,0.0004367978,0.0007822004,0.001238967],"category_scores_gemma":[0.001997566,0.0002118191,0.0007045735,0.0005793383,0.0002722195,0.001114148,0.0005891563,0.0009409044,0.00120472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003446676,"about_ca_system_score_gemma":0.0003099502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002182051,"about_ca_topic_score_gemma":0.006064842,"domain_scores_codex":[0.9997357,0.00006155139,0.00001829939,0.00008791139,0.00005160469,0.00004491308],"domain_scores_gemma":[0.9993266,0.0002532129,0.00009474398,0.00006397818,0.0001999533,0.00006159396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002197467,0.001203591,0.06308144,0.001094525,0.0004565285,0.001410845,0.001363301,0.0622941,0.1828306,0.003498295,0.06303309,0.6175362],"study_design_scores_gemma":[0.00003512564,0.0003279978,0.03219986,0.00006030982,0.0001212452,0.0002457668,0.0005296509,0.9274449,0.02737071,0.004060083,0.00754509,0.00005920275],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7541171,0.001823431,0.2164842,0.0009278261,0.0006316529,0.0002788107,0.01010945,0.006167792,0.009459702],"genre_scores_gemma":[0.879186,0.0004332232,0.09117911,0.0002624972,0.0003084598,0.0002302409,0.01790286,0.000235076,0.01026249],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002182051,"threshold_uncertainty_score":0.004338741,"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."}}