Table 9 RF Results of Filtered-based BERT Similarity Dataset (Word_Antonym).

From: Enhancing Arabic healthcare fake news detection with data augmentation and multi-metric analysis using large language models

Threshold Range

Accuracy(%)

Prec.(%)

Recall(%)

F-score(%)

New Tweets

0.4–1

93.58

94

94

94

1125

0.5–1

92.83

93

93

93

1112

0.6–1

89.81

90

90

90

1093

0.7–1

86.03

87

86

86

1050

0.8–1

83.77

84

84

84

956

0.9–1

80.75

81

81

81

707

Back to article page