Accuracy: 80.63
Papers with Code · CC BY-SA 4.0
Emotion Classification
Emotion classification, or emotion categorization, is the task of recognising emotions to classify them into the corresponding category. Given an input, classify it as 'neutral or no emotion' or as one, or more, of several given emotions that best represent the mental state of the subject's facial expression, words, and so on. Some example benchmarks include ROCStories, Many Faces of Anger (MFA), and GoEmotions. Models can be evaluated using metrics such as the Concordance Correlation Coefficient (CCC) and the Mean Squared Error (MSE).
논문
Accuracy: 82.4
Investigating Shallow and Deep Learning Techniques for Emotion Classification in Short Persian Texts
Macro F1: 0.71
F-F1 score (NA): 0.42F-F1 score (Persian): 0.4F-F1 score (Comb.): 0.34V-F1 score (NA): 0.42
Accuracy: 77.04
Macro-F1: 0.563Micro-F1: 0.707Accuracy: 0.589
Top-1 Accuracy: 74.8
Macro-F1: 0.549Micro-F1: 0.713Accuracy: 0.591
F1: 65.88
F1: 30.29
Accuracy: 66.48Weighted Accuracy: 66.48
Macro-F1: 0.561
Macro-F1: 0.578Micro-F1: 0.713Accuracy: 0.601