Table 7 Results AraBERT of Not-Filtered Dataset (with no similarity).

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

Method

Accuracy(%)

Prec.(%)

Recall.(%)

F-score(%)

WordAntonym

95.13

95

94

95

WordNet

95.81

96

95

95

TF-IDF

93.40

94

93

93

WordEmbeddings_BERTBase

85.80

85

86

85

WordEmbeddings _DistilBERT

84.72

85

84

85

WordEmbeddings _RoBERTa

84.32

84

84

84

Pipeline_random

81.54

81

81

81

Pipeline_sequential

82.61

82

83

82