User Preference-aware Fake News Detection
Disinformation and fake news have posed detrimental effects on individuals and society in recent years, attracting broad attention to fake news detection.
All Publications
Factual Corrections Eliminate False Beliefs About COVID-19 Vaccines
The spread of misinformation about COVID-19 vaccines threatens to prolong the pandemic, with prior evidence indicating that exposure to misinformation has negative effects on intent to take the...
Since the election of Donald Trump to the presidency, a new conspiracy theory has emerged in the United States. According to this theory, a high-ranking federal official known only as “Q” provides...
Mining Dual Emotion for Fake News Detection
Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the...
Mainstreaming of conspiracy theories and misinformation
Parents - particularly moms - increasingly consult social media for support when taking decisions about their young children, and likely also when advising other family members such as elderly...
Where Have All the Data Gone? A Critical Reflection on Academic Digital Research in the Post-API Age
When the Facebook–Cambridge Analytica (CA) scandal burst into the headlines in March 2018, it cast a spotlight on tech companies’ uses and abuses of personal data (Cadwalladr & Graham-Harrison,...
Debunking the Misinfodemic: Coronavirus Social Media Contains More, Not Less, Credible Content
Several high-profile sources have focused worldwide attention on the dangers of misinformation about COVID.
Fact-Enhanced Synthetic News Generation
The advanced text generation methods have witnessed great success in text summarization, language translation, and synthetic news generation. However, these techniques can be abused to generate...
Citizens are asked to buy, and asked to consider to buy, goods of all sizes and all prices, nearly all of the time.
Semantics derived automatically from language corpora contain human-like biases
In this paper researchers show that standard machine learning can acquire stereotyped biases from textual data that reflect everyday human culture. The general idea that text corpora capture...