Public Response To Federal Electronic Cigarette Regulations Observed through the Lens of Social Media: Natural Language Processing and Topic modeling (Preprint)

BACKGROUND E-cigarette use has been a public health issue in the US. On June 23, 2022, the FDA issued marketing denial orders (MDOs) to Juul Labs Inc. for all of their products currently marketed in the United States. However, one day later, on June 24, 2022, a federal appeals court granted a temporary reprieve to Juul Labs that allowed it to keep its e-cigarettes on the market. As the conversation around Juul continues to evolve, it is crucial to gain insights into the sentiments and opinions expressed by individuals on social media OBJECTIVE To better understand the response of the general public to the policy, and the life-cycle of public health-related policy on social media. METHODS 6,023 tweets and 22,288 reply/retweets were collected from Twitter (rebrand as X) between Jun 2022 and October 2022. We conducted a descriptive analysis, topic modelling utilizing the state-of-the-art BERTopic technique, and sentiment analysis. RESULTS We found that the life cycle of reactions to the FDA’s ban on Juul lasted no longer than a week on Twitter. Not only the news related to the announcement itself but the surrounding discussions (the 6 topics presented in the study) diminished shortly after June 23rd, 2022—the date when the ban was officially announced. Of the top 50 most retweeted tweets, we found posters responded from neutral (23/45, 51.11%) to more negatively (19/45, 42.22%) on the corresponding topics. CONCLUSIONS We observed a short life-cycle for this news announcement with more negative sentiment toward the FDA’s ban on JUUL. Policymakers could employ tactics such as ongoing updates and reminders about the ban, highlighting its impact on public health, and actively engaging with influential social media users who can help sustain the conversation.