An Application of Machine Learning Models in Detecting Vietnamese Fake News

An Application of Machine Learning Models in Detecting Vietnamese Fake News

Thuan Ngoc Le (University of Economics of Ho Chi Minh City, Vietnam), Kim Ba Thien Nguyen (University of Economics of Ho Chi Minh City, Vietnam), and Vu Khanh Ngo Tan (University of Economics of Ho Chi Minh City, Vietnam)
Copyright: © 2024 |Pages: 15
DOI: 10.4018/IJSI.362623
Article PDF Download
Open access articles are freely available for download

Abstract

Nowadays, with the development of the Internet, publishing and sharing news has become very easy, and anyone can do it. Along with the increasing amount of information on the internet, besides official information, fake news continues to rise and spreads quickly across the network. Fake news has become a major societal problem, negatively impacting all aspects of economic, cultural, and social life. How to prevent the spread of fake news online is an urgent issue today. To help readers recognize whether news is trustworthy, this paper proposes using natural language processing techniques and machine learning models to detect fake news in posts on the social network Facebook in the Vietnamese language. After the training process, the resulting model can predict whether the news is real or fake. The model's evaluation results are presented according to popular machine learning metrics, and the best-performing model on the dataset used in this paper is the Light Gradient Boosting Algorithm – LGBM – with an accuracy of 88.21% compared to other models used in this paper.
Article Preview
Top

Introduction

Fake news is not a new issue as the term “fake news” has been around since the 19th century when factions used it to compete for power (Zhou et al., 2019), or when the New York Sun reported on life on the moon, or tabloid newspapers published articles mixing true and false information, making it difficult for readers to distinguish real from fake news (Allcott & Gentzkow, 2017). Along with technological advancements, fake news spreads through various types of media, especially social networks, and has increased exponentially in recent times. Fake news is created based on the motives of its creators. Fake news can also stem from real news but be edited in a negative direction, distorting and misrepresenting the truth to deceive readers and alter their perspectives. On the Internet, fake news can be fabricated stories with sensational headlines designed to increase traffic to websites or boost views and likes on social media posts.

Fake news often spreads quickly because it is created to grab attention and provoke emotional responses from readers. People’s easy access to information on social networks, coupled with the lack of legal responsibility for publishing news on these platforms, allows for sensationalism and the rapid, wide dissemination of information. With such rapid and widespread transmission, the harm caused by fake news is enormous. People often make important decisions based on what they read and the consensus they perceive (often based on views and likes on social media) (Silverman, 2016). For example, during the recent COVID-19 pandemic, people frequently believed information circulated on Facebook about using certain drugs to treat COVID-19, despite there being no approved treatment at the time (Apuke et al., 2021). When people cannot differentiate between real and fake news, it creates confusion and misunderstanding about important issues, undermines trust in legitimate news sources, and more importantly, changes people's mindsets, affecting their quality of life, causing public anxiety, and even threatening social order and national security. To combat the fake news problem in Vietnam, the Fake News Handling Center was established with the mission to “Spread the truth” and the operational philosophy that “Fake news is created by humans, so only humans can recognize and handle fake news.” As such, we can imagine that to identify fake news, this center requires a large staff and significant time and cost to verify whether the news is fake.

Fake news is rampant, infiltrating our lives through various media channels with the aim of deceiving people into believing what fake news presents. So, how can we distinguish between fake news and avoid inadvertently sharing misinformation? Currently, many methods for detecting fake news have been introduced, both in mainstream media and by government agencies, which often guide readers on how to identify fake news as follows: check the news source to analyze the content and purpose of the site posting the news; verify the author to confirm the reliability of the news source; check illustrative information such as images and links to see if the information is truly useful or for another purpose; recognize biases to determine whether there is any bias or personal prejudice; distinguish between news and jokes to stay clear-headed and separate real news from internet pranks; check the publication date, as old news republished may not necessarily relate to current events; read the entire article rather than just the headline, as headlines may be sensational to attract readers; seek expert opinions by consulting editors or sources from reputable news outlets (International Federation of Library Associations and Institutions, 2017). However, this identification process is often ineffective as readers typically lack the time to verify or due to psychological factors. Therefore, our goal is to use scientific advancements and machine learning methods to classify real and fake news, helping readers detect fake news and contribute to reducing its spread on social networks, thereby mitigating the harm caused by fake news.

Complete Article List

Search this Journal:
Reset
Volume 13: 1 Issue (2025)
Volume 12: 1 Issue (2024)
Volume 11: 1 Issue (2023)
Volume 10: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 9: 4 Issues (2021)
Volume 8: 4 Issues (2020)
Volume 7: 4 Issues (2019)
Volume 6: 4 Issues (2018)
Volume 5: 4 Issues (2017)
Volume 4: 4 Issues (2016)
Volume 3: 4 Issues (2015)
Volume 2: 4 Issues (2014)
Volume 1: 4 Issues (2013)
View Complete Journal Contents Listing