Journal of Big Data

Table 8 Experiment 2 with AraSenTi dataset

From: AraXLNet: pre-trained language model for sentiment analysis of Arabic

	Precision	Recall	F1-Score	Support
0	0.96	0.91	0.94	1230
1	0.89	0.96	0.93	993
Accuracy	–	–	0.93	2223
Macro Avg	0.93	0.93	0.93	2223
Weighted Avg	0.93	0.93	0.93	2223

Back to article page