Detecting COVID-19-Related Fake News Using Feature Extraction

Abstract

Since its emergence in December 2019, there have been numerous posts and news regarding the COVID-19 pandemic in social media, traditional print, and electronic media. These sources have information from both trusted and non-trusted medical sources. Furthermore, the news from these media are spread rapidly. Spreading a piece of deceptive information may lead to anxiety, unwanted exposure to medical remedies, tricks for digital marketing, and may lead to deadly factors. Therefore, a model for detecting fake news from the news pool is essential. In this work, the dataset which is a fusion of news related to COVID-19 that has been sourced from data from several social media and news sources is used for classification. In the first step, preprocessing is performed on the dataset to remove unwanted text, then tokenization is carried out to extract the tokens from the raw text data collected from various sources. Later, feature selection is performed to avoid the computational overhead incurred in processing all the features in the dataset. The linguistic and sentiment features are extracted for further processing. Finally, several state-of-the-art machine learning algorithms are trained to classify the COVID-19-related dataset. These algorithms are then evaluated using various metrics. The results show that the random forest classifier outperforms the other classifiers with an accuracy of 88.50%.

Differences in college students’ occupational dysfunction and mental health considering trait and state anxiety during the COVID-19 pandemic

“…Thus, the results of our study differed from those of previous studies, which showed that people with low health literacy are more likely to have problems in their lives. Information about the COVID-19 pandemic provided by the media is both trusted and not trusted and has been spread rapidly to keep the public abreast of the global situation and to prevent infection ( Khan et al, 2022 ). In the survey about COVID-19 Information Sources and Mental Health, trusting social media may worsen mental health ( Patwary et al, 2021 ).…”

Fake News Detection Techniques on Social Media: A Survey

“…Khan et al [22] discovered that participants' perceptions of false news transferred to an adjacent brand advertising when they saw an adjacent brand commercial. The direct impact of behavioral intentions on brands is employed to investigate the consequences of fake news.…”

“…It is possible that detecting bogus news early on may assist to prevent it from spreading further on social media platforms. There have been several subjective research into the components of false news published in the social psychology literature [22,32,38,39], but there have been relatively few quantitative investigations to validate these psychological factors. Regarding spreading false information on social media, the echo chamber effect has a tremendous impact, as seen above.…”

“…However, limited research has been undertaken to utilize important visual characteristics for the false news detection challenge, including classic local and global features and recently generated deep network-based features [42]. Several sophisticated approaches have recently been shown, including the ability to edit video recordings of renowned persons [22], create high-quality films [43], and other skills. As a consequence, distinguishing true from false visual information becomes much more difficult and critical, and more complex visual-based criteria are required for this study to be successful [44].…”

“…As a result of these difficulties, "comparative and objective sentences, classification accuracy, and sarcasm are all considered problems in sentiment analysis." Most sentiment analysis models [15,22,32] wrongly classify a considerable portion of opinionated data as neutral, although it is not.…”