Anti-Asian Discourse in Quora: Comparison of Before and During the COVID-19 Pandemic with Machine- and Deep-Learning Approaches

• Author: Sou Hyun Jang,Sangpil Youm,Yong Jeong Yi
• DOI: http://doi.org/10.1177/21533687221134690
• Published date: 01 January 2023
• Date: 01 January 2023
• Subject Matter: Articles

Anti-Asian Discourse in Quora:

Comparison of Before and

During the COVID-19

Pandemic with Machine- and

Deep-Learning Approaches

Sou Hyun Jang

1

, Sangpil Youm

2

,

and Yong Jeong Yi

3

Abstract

The current study attempts to compare anti-Asian discourse before and during the

COVID-19 pandemic by analyzing big data on Quora, one of the most frequently

used community-driven knowledge sites. We created two datasets regarding

“Asians”and “anti-Asians”from Quora questions and answers between 2010 and

2021. A total of 1,477 questions and 5,346 answers were analyzed, and the datasets

were divided into two time periods: before and during the COVID-19 pandemic. We

conducted machine-learning-based topic modeling and deep-learning-based word

embedding (Word2Vec). Before the pandemic, the topics of physical difference and

racism were prevalent, whereas, after the pandemic, the topics of hate crime, the

need to stop Asian hate crimes, and the need for the Asian solidarity movement

emerged. Above all, the semantic similarity between Asian and Black people became

closer, while the similarity between Asian people and other racial/ethnic groups was

diminished. The emergence of negative and radical language, which increased saliently

after the outbreak of the pandemic, and the considerably wider semantic distance

between Asian and White people indicates that the relationship between the two

1

Department of Sociology, Korea University, Seoul, South Korea

2

Department of Computer & Information Science & Engineering, Herbert Wertheim College of

Engineering, University of Florida, Gainesville, FL, USA

3

Department of Data Science, School of Global Convergence, College of Computing & Informatics, ,

Sungkyunkwan University, Seoul, South Korea

Corresponding Author:

Yong Jeong Yi, Department of Data Science, School of Global Convergence, College of Computing &

Informatics, Sungkyunkwan University, 25-2 Sungkyunkwan-ro, Jongno-gu, Seoul, South Korea.

Email: yjyi@g.skku.edu

Article

Race and Justice

2023, Vol. 13(1) 55-79

© The Author(s) 2022

Article reuse guidelines:

sagepub.com/journals-permissions

DOI: 10.1177/21533687221134690

journals.sagepub.com/home/raj

races has been weakened. The f‌indings suggest a long-term campaign or education

system to reduce racial tensions during the pandemic.

Keywords

anti-Asian, hate crime, COVID-19, race and ethnicity, Quora, topic modeling,

Word2Vec

Since the coronavirus disease-19 (COVID-19) was f‌irst discovered in late 2019 in

Wuhan, China (Velavan & Meyer, 2020), anti-Asian hostility has spread world-

wide. The number of hate crimes against Asian people increased by approximately

76% in 2020: from 158 cases in 2019 to 279 in 2020 in the U.S. (Barr, 2021).

Moreover, given that anti-Asian hate crimes are often underreported (Kim et al.,

2022; Lantz & Wenger, 2021), the actual number could be even higher. As the

COVID-19 pandemic has been prolonged, hate crimes against Asian people have

become more severe, increasing by more than 300% between 2021 and 2022 in

the US nationwide and by an astonishing 833% in New York City from to

2019–2020 (Levin, 2021). In most cases, the targets of hate crimes were women

and the elderly (Lyu et al., 2021).

Hatred against Asian people occurred not only in physical spaces but also in

virtual spaces. Previous studies have observed that media exposure can inf‌luence

beliefs and behaviors related to social biases (Cheah et al., 2020; Davidson &

Farquhar, 2020). After former American president Donald Trump referred to the

COVID-19 virus as “the Chinese virus”in a tweet (Trump, 2020) and reports of

the virus/disease being called the “Wuhan virus,”“Chinese f‌lu,”and “Kung Flu”

circulated (Dubey, 2020; Reny & Barreto, 2020), the number of online

anti-Asian hate speeches surged on various social media platforms, including

Twitter, Facebook, and Instagram (He et al., 2021). In fact, over 40% of

Americans have admitted to engaging in at least one discriminatory behavior

toward Asian people (Dhanani & Franz, 2020). More than half of Chinese

American parents with 4–18-year-old children reported experiencing vicarious

online and direct off‌line racism and discrimination during the early phase of the

COVID-19 pandemic (Cheah et al., 2020). According to Lantz and Wenger

(2020), approximately 44% of Asian survey respondents knew someone who had

been a victim of a hate crime during the COVID-19 pandemic.

Asian people reported experiencing greater perceived discrimination as a result of

COVID-19 than other racial/ethnic groups (Liu et al., 2020). This is concerning as per-

ceived racial discrimination and racism have been found to be negatively associated

with both better physical (Gee et al., 2009; Misra et al., 2021) and mental health

among racial/ethnic minorities (Cheah et al., 2020; Gee, Spencer, et al., 2007; Gee,

RO, et al., 2009; Hwang & Goto, 2008; Nadal et al., 2015). During the COVID-19

pandemic, Asian Americans were more mentally vulnerable than their White counter-

parts due to the prevalent anti-Asian environment and violence in both online and

56 Race and Justice 13(1)