Journal of Big Data

Table 2 Normalization techniques used by different researchers

From: Investigating the impact of pre-processing techniques and pre-trained word embeddings in detecting Arabic health information on social media

Replace	With	Relevant studies
أ, إ, and آ	Bare-alif ا	[21, 24, 26, 71, 74, 92,93,94,95,96,97]
ى	ي	[23, 26, 78, 84, 93,94,95,96,97,98]
ي and ئ	ى	[92]
ىء and ئ	ي	[78]
ؤ and ئ	ء	[77, 94, 96, 99, 100]
ئ	ى	[85]
ة	ه	[20, 74, 85, 94,95,96,97, 99,100,101]
چ	ج	[100]
ڤ	ف	[100]
ءى and ءي	ئ	[71]
ص	س	[24]
ض	ظ	[24]
ؤ	و	[71, 78, 99]
كـ	ك	[38, 77]

Back to article page