Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Machine learning classifiers with pre-processing techniques for rumour detection on social media: an empirical study

Machine learning classifiers with pre-processing techniques for rumour detection on social media:... 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. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png International Journal of Cloud Computing Inderscience Publishers

Machine learning classifiers with pre-processing techniques for rumour detection on social media: an empirical study

Loading next page...
 
/lp/inderscience-publishers/machine-learning-classifiers-with-pre-processing-techniques-for-rumour-e83cs3vrMM

References

References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.

Publisher
Inderscience Publishers
Copyright
Copyright © Inderscience Enterprises Ltd
ISSN
2043-9989
eISSN
2043-9997
DOI
10.1504/ijcc.2022.124797
Publisher site
See Article on Publisher Site

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.

Journal

International Journal of Cloud ComputingInderscience Publishers

Published: Jan 1, 2022

There are no references for this article.