Table 6. Performance comparison of deep learning classifiers using Daraz and Yelp datasets.

Deep Learning Classifiers	Daraz Dataset				Yelp Dataset
	Precision	Recall	F1 Score	Accuracy	Precision	Recall	F1 Score	Accuracy
BERT	71.22	72.41	72.55	73.07	75.87	76.25	77.11	79.89
LSTM	72.44	73.21	73.88	74.12	80.85	81.02	82.14	83.14
GRU	73.96	75.55	74.88	76.55	82.14	84.10	85.11	86.21
CNN	77.15	79.21	78.11	81.31	85.78	87.14	88.47	89.41