Emotion Classification

17 benchmarks458 papers

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).

Benchmarks

Emotion Classification on CMU-MOSEI

AccuracyWeighted Accuracy

Emotion Classification on SemEval 2018 Task 1E-c

Macro-F1AccuracyMicro-F1

Emotion Classification on EWALK

Accuracy

Emotion Classification on MFA

F-F1 score (Comb.)F-F1 score (Persian)V-F1 score (Comb.)V-F1 score (NA)F-F1 score (NA)V-F1 score (Persian)

Emotion Classification on ROCStories

F1

Emotion Classification on ArmanEmo

Macro F1

Emotion Classification on CAER-Dynamic

Accuracy

Emotion Classification on RAVDESS

Top-1 Accuracy

Emotion Classification on ShortPersianEmo

Macro F1