Machine learning classifiers with pre-processing techniques for rumour detection on social media: an empirical study
by Mohammed Al-Sarem; Muna Al-Harby; Faisal Saeed; Essa Abdullah Hezzam
International Journal of Cloud Computing (IJCC), Vol. 11, No. 4, 2022

Abstract: The rapid increase in popularity of social media helped the users to easily post and share information with others. However, due to uncontrolled nature of social media platforms, such as Twitter and Facebook, it becomes easy to post fake news and misleading information. The task of detecting such problem is known as rumour detection. This task requires data analytics tools due to the massive amount of shared content and the rapid speed at which it is generated. In this work, the authors aimed to study the impact of different text pre-processing techniques on the performance of classifiers when performing rumour detection. The experiments were performed on a dataset of tweets on emerging breaking news stories which cover several events of Saudi political context (EBNS-SPC). The results have shown that pre-processing techniques have a significant impact on increasing the performance of machine learning methods such as support vector machine (SVM), multinomial naïve Bayes (MNB), and K-nearest neighbour (KNN) classifiers. However, the classifiers react differently when different combinations of pre-processing techniques were used.

Online publication date: Tue, 09-Aug-2022

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Cloud Computing (IJCC):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com