Related Experiment Video
Updated: Jun 5, 2026
08:39
Generation of Electronic Cigarette Aerosol by a Third-Generation Machine-Vaping Device: Application to Toxicological Studies
Published on: August 25, 2018
Spatiotemporal analysis of electronic cigarette discussion on Twitter/X using natural language processing
Zidian Xie1, Jiamu Tang2, Dongmei Li3
1Clinical and Translational Science Institute, University of Rochester Medicine, The United State of America, 265 Crittenden Boulevard CU, Rochester, NY, 420708, 14642-0708, USA. zidian_xie@urmc.rochester.edu.
BMC Public Health
|June 4, 2026
Summary
Online discussions about electronic cigarettes (e-cigarettes) on Twitter/X show varying sentiments across countries and time. E-cigarette users express more positive views than non-users, highlighting differing perspectives on vaping.
Area of Science:
- Public Health
- Social Media Analysis
- Tobacco Control
Background:
- Electronic cigarettes (e-cigarettes) have gained significant popularity, especially among young demographics.
- Understanding online discourse patterns is crucial for public health initiatives.
Purpose of the Study:
- To analyze the spatiotemporal trends and sentiment patterns of electronic cigarette discussions on Twitter/X.
- To differentiate sentiments between e-cigarette users and non-users.
Main Methods:
- Collected over 3 million e-cigarette-related tweets from March 2021 to March 2023 via the Twitter API.
- Utilized human coders and a RoBERTa model for sentiment analysis and topic modeling (LDA) on 2,300 tweets.
- Filtered for 2,140,439 non-commercial tweets to identify discussion patterns.
Main Results:
- Observed an increase in e-cigarette tweets, particularly in the UK and Australia.
- Positive sentiment (27.0%) slightly outweighed negative sentiment (23.3%), with neutral tweets comprising nearly half.
- E-cigarette users showed significantly higher positive sentiment (41.19%) compared to non-users (9.74%).
Conclusions:
- Online sentiment regarding e-cigarettes is dynamic and geographically diverse.
- Distinct sentiment differences exist between e-cigarette users and non-users on social media.
- Findings offer insights for monitoring online discourse and informing tobacco regulatory strategies.
