Detecting Misleading Information on COVID-19 : A Machine Learning Perspective

Main Article Content

M.Arunkrishna et. al.

Abstract

Online Social networks become a popular way for sharing information among people. With increasing technology like Wi-Fi, Wi-Max ,3G/4G along with handheld devices like smartphones and tablets, popular applications such as Instagram, Facebook, Twitter and YouTube, becomes a dominant platform for  news and entertainment. The extensive use of these social networks has an incredible influence on sharing news among people It holds both positive and negative effects of its own. Because of it’s high popularity,Online Social Networks(OSNs),has become the target for spammers. Also, false news for different political and commercial purpose has been evolving in the large count and spread worldwide. After the spread of COVID-19, there had been a lot of confusion and pitfalls on the topic of who to believe and who should be rejected. With the advent of time, several companies like Facebook, and Twitter joined hands to identify the news and regard it authentic or not. This effort was very hard for people, as the news are spreading at a rapid pace, no matter how many people are upon the task, the rate of expansion of news is always faster than the rate of evaluation of whether the news is authentic or not. Additionally, it can be observed that the news cannot be regarded as fake or true before careful evaluation. This evaluation is based on the results. So it is important to create a method for identifying fake news and distinguishing it from individuals. Thus, the paper evaluates several models in order to find the best fit with the highest level of accuracy.

Downloads

Download data is not yet available.

Metrics

Metrics Loading ...

Article Details

How to Cite
et. al., . M. (2021). Detecting Misleading Information on COVID-19 : A Machine Learning Perspective. Turkish Journal of Computer and Mathematics Education (TURCOMAT), 12(3), 4918–4926. Retrieved from https://turcomat.org/index.php/turkbilmat/article/view/2000
Section
Research Articles