Skip to main content

Table 3 Techniques used as brute-force algorithms in each attempt for all algorithms

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

Techniques used

Parameters or range used

Number of features

Ranges from 7,000 to 18,000

N-gram

(1, 1), (1, 2), (1, 3), (1, 4)

Feature selection

Count vectorizer and TF-IDF