Table 3. English datasets.

‘Train’ represents the training set and ‘Test’ represents the test set. For the IMDB dataset, ten-fold cross-validation was used to split the training and testing sets).

Datasets	Positive(Pos)		Negitive (Neg)
	Train	Test	Train	Test
IMDB	1,000		1,000
Twitter	1,561	173	1,560	173
Lap14	994	341	870	128
Rest16	1,240	469	439	117