Affective Engagement in #StopAAPIHate on Social Media: The Role of Emotion in Driving Engagement for Counter-hate Content on Twitter

Zifei Fay Chen (Communication Studies, CAS), June Y. Lee (Entrepreneurship, Innovation, Strategy, and International Business, SOM), Shan Wang (Data Science, CAS), Diane Woodbridge (Data Science, CAS)

 

Since the outbreak of the COVID-19 global pandemic in early 2020, the Asian American and Pacific Islander (AAPI) communities have experienced an uptick of anti-AAPI discrimination, racism, and hate incidents. These hate incidents range from individual acts of shunning, verbal harassment, and physical attacks, to civil rights violations including refusal of service and workplace discrimination. According to Stop AAPI Hate, a total of 10,905 anti-AAPI incidents were reported from March 19, 2020 to December 31, 2021, causing significant detrimental impact on AAPI persons’ mental health. Importantly, scholars and activists have noted that these anti-AAPI hate incidents are not only associated with the anti-AAPI rhetoric during the COVID-19 pandemic, but also have their historical roots of anti-AAPI discrimination and racism, such as the “perpetual foreigners” and “Yellow Peril” stigmas, as well as the “model minority” myth that was used to delegitimaze and silence concerns from the AAPI communities.  

To cope with racial trauma, many AAPI persons have turned to social media to view related content, share information, participate in online communities/forums, and join discussions. Besides being a coping tool, social media can  also be a tool to advocate for counter-hate messages and facilitate social movement.  Previous social media research has highlighted the role of emotion, where it was suggested that by engaging with emotion-carrying content on social media, people can better regulate their emotions and reconstruct their emotional episodes. In this Interdisciplinary Action Group project supported by CRASE, we set out to explore if and how emotion may drive engagement in counter-hate content on Twitter during the #StopAAPIHate movement. 

We drew insights from the emotion theories, social media engagement literature, and used machine learning and computational methods to analyze data. To delineate a more nuanced understanding, we focused on two types of frameworks in our categorization and analyses of emotion: (1) the valence approach where emotion was categorized into positive, negative, and neutral, and (2) the discrete approach where emotion was further categorized into joy, sadness, anger, fear, surprise, and disgust. 

Data Collection

Using Twitter API for Academic Research, we collected tweets between January 1, 2020 to August 31, 2021. The retrieval search criteria included 1) tweets written in English and 2) tweets with at least one of the following hashtags: #StopAAPIhate, #StopAsianhate,  #IAmNotAVirus, #WashTheHate, #RacismIsAVirus, #IAmNotCovid19, #BeCool2Asians, and #HateIsAVirus, resulting in a total of 1,773,683 tweets. 

To identify sentiment (negative, positive, and neutral) and the existence of six discrete emotions (joy, sadness, anger, fear, disgust, and surprise) in the tweets, we used the RoBERTa model, the robustly optimized Bidirectional Encoder Representations from Transformers (BERT) Pre-training Approach. 

We then applied the developed models for sentiment/valence analysis and discrete emotion classification. Further, we developed a regression model and applied feature importance to understand the valence and discrete emotions affecting the level of engagement (likes, retweets, and replies) towards a tweet.

Preliminary Findings

Emotional valence reflected in the counter-hate content on Twitter

Among all tweets collected, about 22.7% were negative, 25.3% were positive, and 52% were neutral. In this analysis, one tweet may only include one valence. 

Discrete emotions reflected in counter-hate content on Twitter

Among the tweets collected, about 21.5% contained anger, 17.4% contained sadness, 11.9% contained joy, 5% contained disgust, 2.1% contained fear, and 1% contained surprise. In this analysis, a single tweet may include multiple emotions or no emotion. 

The impact of emotional valence and discrete emotions on social media engagement

Emotional valence was a moderate predictor of the number of favorites, retweets, and replies, along with other tweet features including hashtag counts, referencing another tweet, multimedia attachment, and replying to other users. For discrete emotions, the emotion of anger, sadness, and disgust were predictors of the number of favorites, retweets, and replies, along with other tweet features including hashtag count, referencing another tweet, multimedia attachment, and replying to other users. Particularly for replies, joy was also shown as a predictor in driving the volume of replies. 

Next Steps and Implications

The current stage of the project has demonstrated the features that drive engagement in counter-hate content on Twitter. For the next steps of the study, we will continue building models that inform the direction and magnitude of the effects specifically from each emotional valence and discrete emotion. Using these research insights, we hope to achieve a more in-depth and nuanced understanding of the effects from emotional valence and discrete emotions in driving further engagement in counter-hate content. And in order to achieve this engagement, we will provide greater empirical communication evidence from the large data set to further support the #StopAAPIHate movement on social media.

Faculty Spotlight: Annette Regan

Annette K Regan is Assistant Professor and Co-Director of the Community Public Health Practice Concentration in Orange County, CA

When did you realize you had a passion for epidemiology?

I didn’t know what epidemiology was until I was in my fourth year of psychology in undergrad. I was about to graduate, and I was trying to figure out what I was going to do next. I was volunteering in a sleep lab, and one of my coworkers was talking about epidemiology. I started looking into it, and it sounded perfect for me. It was math plus health plus all these things I liked all in one field. On my first day in epidemiology class during my MPH at Emory I thought, “This is where I belong.” Epi is one of the best fields. We can tackle all of these different health problems and use data and data science to better understand important health problems and identify effective solutions. 

How did you end up at USF?

My family was transitioning back to the US from Australia, and we were looking for a place where our family could be happy and grow. My husband and I settled on southern CA – he works for the State Lands Commission (oil and gas guy) and fortunately USF was hiring for a MPH faculty in Orange County to extend their MPH program. Starting this MPH program in OC sounded really exciting. And our family is definitely settled here – we welcomed our son right before I started at USF!

Can you describe some of your recent work?

Right now I’m really busy with COVID-19 vaccine evaluation. I recently completed a series of papers on COVID-19 infection during pregnancy and how it affects the health of the mother and the infant.  I’ve just launched a large study looking at COVID-19 vaccine safety and effectiveness in mothers and babies. Another big study I’m working on in collaboration with Boston University is a preconception cohort study to examine vaccine exposure around the time of conception and whether it influences the risk of miscarriage. We recently published a paper showing that vaccination is not associated with fertility but that COVID-19 infection in the male partner could reduce one’s chances of getting pregnant. It might be my favorite paper I’ve worked on, because it’s the only research I’ve ever done that was mentioned on SNL! Anthony Fauci also talked about it to try to dispel these myths about the COVID-19 vaccine and fertility.  

I think it’s also important to acknowledge other impacts the COVID-19 pandemic has had beyond infection. In addition to examining the direct health impacts of COVID-19, I’m also currently leading a large cohort study on the mental and societal impacts of COVID-19 on pregnant individuals, their partners, and their babies. It’s been very meaningful to learn from parents about their experiences birthing and parenting during the pandemic.

What has it been like doing so much research on COVID and vaccines during this pandemic?

Interestingly, I didn’t originally want to do COVID-19 research because I knew everyone was going to be doing it. I supported some student work looking at the impact of COVID-19 on childhood vaccination, but felt like I didn’t want to take on COVID-19 research myself. It’s a tough field. Almost any project you start to draft up has already been published five times by the time you get started. But, I’ve been doing influenza research for so long, all of my influenza colleagues were entirely consumed by COVID-19 work, and I just knew I was going to have to start doing this work eventually. Just as I was coming back from maternity leave, the recommendations started to come out for COVID-19 vaccination during pregnancy, so this was my sign that I could not continue to do the type of research that I do around respiratory diseases and vaccines and without including COVID-19. 

How do you bring the themes of your research to your courses at USF?

This past Fall, I offered a vaccine epidemiology course for the first time. It was a really fun course to teach and I think the students got a lot out of it. There has never been a better time to teach about vaccines than during a pandemic!

I also get a lot of students who are interested in doing research, so I have a few Research Assistants and volunteers who are helping with my cohort study. I bring in a lot of my own research as examples in my classes especially when teaching epidemiology methods. 

What are you planning on doing next?

Taking a nap. But seriously, what I really want to do is continue to grow this COVID-19 research area with pregnant individuals. They are a really high risk group, but they have the lowest vaccination rates. I want to use the results of my work to co-design interventions with communities to improve maternal immunization rates. There’s a lot of work that needs to be done to increase these vaccination rates. I also want to build more of a team and further mentor junior scientists to do this work. I really want to develop the next generation of scientists in this area.