Exploring Perceptions of Social Movements on Social Media during COVID-19

The prevalence and impact of hate speech on social media platforms, including Twitter, have been extensively documented in the literature. This research has explored the perceptions of social movements in social media during the pandemic, specifically within the context of the StopAsianHate movement, which emerged in response to the increasing incidents of anti-Asian hate crimes and hate speech during the COVID-19 pandemic. The findings reveal that the conversations within the StopAsianHate movement on Twitter can be broadly categorized into two themes: reporting of hate crimes and hate speech incidents, and the spread of advocacy of the movement through support and initiatives. This research has also explored and defined distinctive levels of hate speech based on intensities within this context, which has led to building a classifier using transfer learning techniques for representation of the defined hate levels to categorize the intensities of anti-Asian hate speech with an accuracy and recall of 0.73. This research contributes to the field of hate speech detection by providing a novel methodology for categorizing hate speech tweets and analyzing the levels of hate speech in social media.