Integrating BERT Embeddings and BiLSTM for Emotion Analysis of Dialogue

Table 3

Results of ablation study experiment on the weighted avg.

Models	Precision	Recall	F1-score
BERT-BiLSTM	0.5886	0.5945	0.5872
BERT-sentence	0.5905	0.5938	0.5899
BiBERT-BiLSTM	0.6020	0.6011	0.5981