Detecting COVID-19 Fake News on Social Media across Four Languages: Followers, Emotions, Relationships, and Uncertainty
Funding Scheme
Senior Research Fellow Scheme (RGC)
Funding Amount
HK$7,798,380
Awarded Year
2022
Identifying and combatting fake news on social media
Fake news about the COVID-19 pandemic misled many people to eschew vaccines, masks and social distancing, putting public health at risk. This research develops deceptive writing theory to identify online messages linked to COVID-19 fake news and its dissemination within and across networks, to operationalize this theoretical model with artificial intelligence (AI) / machine learning (ML) and advanced statistics, to determine how COVID-19 tweets spread within and across communities and their antecedents across levels, and to create an AI/ML-based dashboard to track the diffusion of COVID fake news tweets within and across online communities in real time.
Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. The research team contributes towards the following SDG(s):
By identifying deceptive writing tactics and adding them to fake news detection algorithms and dashboards, we improve students’ and the public’s media literacy, while declawing fake news writers.
Current fake news detection methods either rely on black-box machine learning or painstakingly and unreliably examines authors' history, goals, perspectives, and tactics—especially when fake news is mixed with true news. By contrast, we theorize and test linguistic markers of fake news (e.g., complex vocabulary, emotional tone, audience relationship, and uncertainty) in addition to author identity and follower count. Hence, our approach is both accurate and explainable.
Our research provides direct methods for detecting fake news, including a real-time fake news detection dashboard designed to help students and the public learn and evaluate their media literacy. By enhancing digital media literacy, particularly among students, we empower them to identify fake COVID-19 news and other misinformation quickly, which fosters better decision-making and ultimately saves lives. The impact of our research is broad, benefiting anyone seeking the truth in an age of misinformation and promoting a more informed and resilient global society.
Selected Publications
| Journal articles |
|---|
|
| Keynote/Invited speeches |
|
|
|
|
