Table 7. Performance of the multi-class situational information classification models trained and evaluated using ArCOV19-Sit.

Boldface represents the performance scores of the best ML classifier and the best transformer-based for each metric.

Classifier	Accuracy	Macro-P	Macro-R	Macro-F1	Micro-F1
SVM	73.39%	54.38%	52.79%	53.07%	73.39%
RF	66.83%	59.16%	44.18%	46.78%	66.83%
XGBoost	73.23%	56.54%	49.71%	51.47%	73.23%
AraBERT	77.5%	67.56%	58.79%	61.24%	77.5%
AraBERT-COV19	78.81%	73.96%	77.3%	73.45%	78.81%
AraBERTv02-Twitter	77.99%	64.66%	76.62%	66.58%	77.99%
MARBERT	79.31%	58.9%	58.11%	58.28%	79.31%
XLM-R	77.83%	61.19%	58.57%	59.37%	77.83%