JMIR Publications

ABSTRACT

Background:

Since March 2020, companies nationwide have started work from home (WFH) due to the rapid increase of COVID-19 confirmed cases in an attempt to help prevent the coronavirus from spreading and rescue the economy from the pandemic. Many organizations have conducted surveys to understand people's opinions towards WFH. However, the contributions are limited due to small sample size and the dynamic topics over time.

Objective:

The study aims to understand the U.S. public opinions on working from home during the COVID-19 pandemic.

Methods:

We conduct a large-scale social media study using Twitter data to portrait different groups who have positive/negative opinions about WFH. We perform an ordinary least square regression to investigate the relationship between the sentiment about WFH and user characteristics including gender, age, ethnicity, median household income, and population density. To better understand public opinion, we use latent Dirichlet allocation to extract topics and discover how tweet contents relate to people's attitude.

Results:

After performing the ordinary least square regression using a large-scale dataset (N=58,345) of publicly available Twitter posts concerning working from home ranging from April 10, 2020 to April 22, 2020, we confirm that sentiment of working from home vary across user characteristics. In particular, females (0=Female, 1 = Male) tend to be more positive about working from home (p < .001). People in their 30s (0=No, 1 = Yes) are more positive towards WFH than other age groups (p < .001). People from urban areas (0 = No, 1 = Yes) are more pro-WFH (p < .001). High-income people are more likely to have positive opinions about working from home (p < .001). These nuanced differences are supported by a more fine-grained topic analysis. At a higher level, we find that negative sentiment about WFH roughly corresponds to the discussion of unemployment issues. However, people express more positive sentiment when talking about WFH experience. Furthermore, topic distributions vary across different user groups. Females talk more about WFH experience (p < .05). Older people talk more about unemployment and government (p < .05).

Conclusions:

This paper presents a large-scale social media-based study to understand the U.S. public opinions on working from home during the COVID-19 pandemic. We hope this study can lend itself to making policies both at national and institution/company levels to improve the overall population's experience of working from home.