Journal of Big Data

Table 14 Optimal hyperparameters of the BLSTM

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

	Mazajak sg	Mazajak cbow	Fasttext	ArWordVec sg	ArWordVec cbow	arvec sg	AraVec cbow
Neurons	280	360	20	500	500	500	500
Drop rate	0.2	0	0.5	0.3	0.2	0.5	0.2
Drop rate	0.2	0	0	0.2	0	0	0
Learning rate	0.001	0.001	0.01	0.001	0.001	0.01	0.01
Batch size	120	40	40	300	300	40	300

Back to article page