{"id":"W4210261633","doi":"10.1109/icmla52953.2021.00037","title":"Emotion Recognition and Sentiment Classification using BERT with Data Augmentation and Emotion Lexicon Enrichment","year":2021,"lang":"en","type":"article","venue":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Lexicon; Computer science; Sentiment analysis; Emotion detection; Emotion recognition; Emotion classification; Social media; Artificial intelligence; Natural language processing; 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":[0.0003297841,0.000173053,0.0001553672,0.0001839419,0.0003394609,0.000555961,0.0001999297,0.00005696436,0.00007644458],"category_scores_gemma":[0.00002137762,0.0001687171,0.0000214711,0.000265424,0.00005359619,0.0006598872,0.0001655034,0.000201143,0.00001417973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005753181,"about_ca_system_score_gemma":0.00006298038,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006306983,"about_ca_topic_score_gemma":0.00002209048,"domain_scores_codex":[0.9983202,0.0001314114,0.0002894847,0.0007604154,0.0003596449,0.0001388236],"domain_scores_gemma":[0.9990342,0.00006585519,0.0002581016,0.0003086593,0.0002477945,0.00008542939],"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":[0.00007098116,0.0004601241,0.02709297,0.00006983698,0.0003726268,0.000009249811,0.001119525,0.001224319,0.05426091,0.07009204,0.0001231884,0.8451042],"study_design_scores_gemma":[0.0007337594,0.00008660671,0.007390575,0.0001326688,0.00007109435,0.00004832272,0.0006736509,0.984991,0.001518524,0.001303756,0.002784159,0.0002659296],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2325486,0.0002843906,0.759523,0.00482521,0.0001912826,0.0003727923,0.00004919088,0.00008038967,0.002125061],"genre_scores_gemma":[0.9731921,0.001507959,0.02256547,0.0001386869,0.0001531572,0.0000478401,0.001782327,0.00001327156,0.0005991686],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9837666,"threshold_uncertainty_score":0.6880085,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1363995026874109,"score_gpt":0.3536201657003329,"score_spread":0.217220663012922,"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."}}