Improvement of a Machine Learning Model Using a Sentiment Analysis Algorithm to Detect Fake News: A Case Study of Health and Medical Articles on Thai Language Websites

Improvement of a Machine Learning Model Using a Sentiment Analysis Algorithm to Detect Fake News: A Case Study of Health and Medical Articles on Thai Language Websites

Kanokwan Atchariyachanvanich, Chotipong Saengkhunthod, Parischaya Kerdnoonwong, Hutchatai Chanlekha, Nagul Cooharojananone
Copyright: © 2024 |Pages: 26
DOI: 10.4018/JCIT.344812
Article PDF Download
Open access articles are freely available for download

Abstract

These days, the problem of fake news has grown to be a major social and personal concern. With the amount of information generated through social media, it is very crucial to be able to detect and properly take care of that fake information. Previous studies proposed a machine learning model to detect fake news in online Thai health and medical articles. Still, the problem of detecting fake news with similar content but different objectives exists, and the accuracy of the model needs improvement. Therefore, this study aims to solve these problems by adding 33 new features, including textual features, sentiment-based features, and lexicon features, i.e., herbs, fruits, and vegetables, to identify the objective of an article. We trained and tested the model's prediction accuracy on a new dataset containing 582 reliable and 435 unreliable (fake news) articles from eight Thai websites. Our improved classification model using XGBoost with Lasso, the best feature selection method, achieved an accuracy of 97.76% without over-fitting, reflecting a 7.16% improvement over our earlier model.
Article Preview
Top

Literature Review

Approaches to Identify Fake News in Health and Medical Articles

While many definitions encompass the broader phenomenon of fake news (Fake-news, n.d.a; Fake-news, n.d.b; Molina et al., 2021; Wu et al., 2019), various checks can be used to detect fake news in health and medical reporting (Treharne & Papanikitas, 2020). There are four areas of validation that can help identify fake news stories. First, the news story should be searched on the media publication’s official site or, if available, in the hardcopy newspaper to verify its authenticity from the original source. Second, the reader should check to see if the content in question appears on other reputable websites. This is referred to as “scope of coverage.” Third, fact-checking sites, such as Snopes.com and Factcheck.org, which list current fake news stories, should be consulted. Finally, a generic search of the publication title should be conducted to see if the news item is from a parody publication (Treharne & Papanikitas, 2020).

In Thailand, the Antifakenewscenter.com website is maintained by the Anti-Fake News Center managed by the Ministry of Digital Economy and Society (MDES, n.d.a). This agency collects news on various topics, verifies their content as fake news (or not), and then publishes them on the website. The agency aims to help people become aware of fake news and helps prevent the spread of fake news (MDES, n.d.a). The center labels the types of fake news that have a wide impact, because fake news directly affects people's lives and assets, creates social divisions and misconceptions about society, and destroys the image of the country (Shu et al., 2017).

Figure 1 illustrates an example of a health and medical fake news article from the Anti-Fake News Thailand website. The title, “Lime Soda Cures Cancer,” went viral on social media. Articles in Thailand are popular for educating people on cures for various diseases. If the published articles are unreliable, they may harm people reading them because an unsuitable diet has a negative impact on the body. Vegetables, fruits, and herbs are frequently used to treat various diseases. In addition, unreliable articles often refer to specific diseases such as cancer, diseases of the brain, and other organs.

Figure 1.

Typical Fake News Article: The Title Translates As “Lime Soda Cures Cancer,” Taken From the Government Anti-Fake News Center (MDES, n.d.b)

JCIT.344812.f01

Complete Article List

Search this Journal:
Reset
Volume 26: 1 Issue (2024)
Volume 25: 1 Issue (2023)
Volume 24: 5 Issues (2022)
Volume 23: 4 Issues (2021)
Volume 22: 4 Issues (2020)
Volume 21: 4 Issues (2019)
Volume 20: 4 Issues (2018)
Volume 19: 4 Issues (2017)
Volume 18: 4 Issues (2016)
Volume 17: 4 Issues (2015)
Volume 16: 4 Issues (2014)
Volume 15: 4 Issues (2013)
Volume 14: 4 Issues (2012)
Volume 13: 4 Issues (2011)
Volume 12: 4 Issues (2010)
Volume 11: 4 Issues (2009)
Volume 10: 4 Issues (2008)
Volume 9: 4 Issues (2007)
Volume 8: 4 Issues (2006)
Volume 7: 4 Issues (2005)
Volume 6: 1 Issue (2004)
Volume 5: 1 Issue (2003)
Volume 4: 1 Issue (2002)
Volume 3: 1 Issue (2001)
Volume 2: 1 Issue (2000)
Volume 1: 1 Issue (1999)
View Complete Journal Contents Listing