Table 39.

Best results achieved for each dataset by adapting the Transformer-based models using strategies InData, LOO, and AllData

Dataset	Accuracy			$F_1$-macro
	%	Classifier	Model	%	Classifier	Model
Iro	83.33	LR	BERTweet-LOO	77.24	SVM	BERTweet-LOO
Sar	80.66	MLP	RoBERTa-LOO	79.35	MLP	RoBERTa-LOO
Ntu	93.89	LR	BERTweet-LOO	93.66	LR	BERTweet-LOO
S15	94.39	MLP	BERTweet-LOO	87.31	MLP	BERTweet-LOO
Stm	92.75	SVM	BERTweet-LOO	92.73	SVM	BERTweet-LOO
Per	88.52	MLP	BERTweet-LOO	86.14	LR	BERTweet-LOO
Hob	89.5	MLP	RoBERTa-InData	88.0	MLP	RoBERTa-InData
Iph	87.8	LR	BERTweet-InData	85.8	LR	BERTweet-AllData
Mov	91.1	LR	BERTweet-AllData	85.4	LR	BERTweet-AllData
San	91.6	LR	BERTweet-AllData	91.5	LR	BERTweet-AllData
Nar	97.0	SVM	BERTweet-AllData	96.8	MLP	BERTweet-AllData
Arc	92.1	MLP	BERTweet-AllData	91.9	MLP	BERTweet-AllData
S18	90.9	SVM	BERTweet-AllData	90.8	SVM	BERTweet-AllData
OMD	89.77	SVM	BERTweet-LOO	88.99	SVM	BERTweet-LOO
HCR	82.21	XGB	BERTweet-LOO	77.9	SVM	BERTweet-AllData
STS	95.2	SVM	BERTweet-AllData	94.5	SVM	BERTweet-AllData
SSt	89.1	SVM	BERTweet-AllData	88.9	SVM	BERTweet-AllData
Tar	87.7	SVM	BERTweet-AllData	87.7	SVM	BERTweet-AllData
Vad	93.14	LR	BERTweet-LOO	92.05	LR	BERTweet-LOO
S13	90.4	LR	BERTweet-InData	88.3	LR	BERTweet-InData
S17	93.6	SVM	BERTweet-AllData	93.17	SVM	BERTweet-LOO
S16	91.8	SVM	BERTweet-AllData	90.1	SVM	BERTweet-AllData