JMIR Publications

ABSTRACT

Background:

The 2019 Novel Coronavirus Disease (COVID-19) pandemic has necessitated a rapid shift in how individuals interact and receive fundamental services, including health care. While telemedicine is not a novel technology, previous studies have suggested mixed opinions surrounding its utilization. However, a dearth of research exists on how these opinions have evolved over the course of the present pandemic.

Objective:

Evaluate how the language and sentiment surrounding telemedicine within the context of COVID-19 evolved throughout the early stages of the pandemic.

Methods:

COVID-19 tweets within a pre-existing repository were rehydrated and curated to only include those between January 21st and May 31st, 2020 that related to telemedicine and associated technologies. A comparator sample of identical size (ntweets = 11,479) was generated to compare telemedicine-COVID tweets to general-COVID tweets made during the same time period. Sentiment analysis was performed on both data sets in aggregate in addition to a subset of tweets generated by the top-100-most-and-least-followed accounts.

Results:

Telemedicine gained prominence through the early stages of the pandemic; while more tweets on telemedicine were made during April and May, tweets made in March had significantly more likes and retweets (P < .001). Positive terms (such as “support,” “free,” and “safe) appeared in significantly more tweets than negative terms (such as “crisis,” “outbreak, and “virus”) within the telemedicine-COVID data set in April and May (P < .001), while the reverse was true in February (P < .001). A higher proportion of sentiment-labeled words within the telemedicine-COVID data set were positive (49%) compared to the general-COVID data set (30%, P < .001). The most followed accounts in both the telemedicine-COVID data set and the general-COVID data set were news organizations and individual politicians, and tweets by the top-100-most-followed authors in the telemedicine-COVID data set contained a significantly higher proportion of positive words compared to the general-COVID data set (54% vs. 31%, P < .001).

Conclusions:

Opinions surrounding telemedicine evolved throughout the early stages of the pandemic to become more positive, especially when compared to the larger pool of COVID-19 tweets. Decision makers should capitalize on these shifting public opinions to invest in telemedicine infrastructure and ensure its accessibility and success in a post-pandemic world.