Harm in Layers: Compositions of Misinformative Hate in Anti-Asian Speech and Their Impacts on Perceived Harmfulness

During times of crisis, heightened anxiety and fear create fertile ground for hate speech and misinformation, as people are more likely to fall for and be influenced by it. This paper looks into the interwoven relationship between anti-Asian hatred and COVID-19 misinformation amid the pandemic. By analyzing 785,798 Asian hate tweets and surveying 308 diverse participants, this empirical study explores how hateful content portrays the Asian community, including its truthfulness and targets, as well as what makes such portrayals harmful. We observed a high prevalence of misinformative hate speech that was lengthier, less emotional, and expressed more motivational drives than general hate speech. Overall, we found that anti-Asian rhetoric was characterized by an antagonism and inferiority framing, with misinformative hate underscoring antagonism and general hate emphasizing calls for action. Among all entities being explicitly criticized, China and the Chinese were constantly named to assign blame, with misinformative hate more likely to finger-point than general hate. Our survey results indicated that hateful messages with misinformation, demographic targeting, or divisive references were perceived as significantly more damaging. Individuals who placed less importance on free speech, had personal encounters with hate speech, or believed in the natural origin of COVID-19 were more likely to perceive higher severity. Taken together, this work highlights the distinct compositions of hate within misinformative hate speech that influences perceived harmfulness and adds to the complexity of defining and moderating harmful content. We discuss the implications for designing more context- and culture-sensitive counter-strategies and building more adaptive and explainable moderation approaches.