Investigating the Attitudes of Adolescents and Young Adults Towards JUUL: Computational Study Using Twitter Data
Bibliographic record
Abstract
BACKGROUND: Increases in electronic nicotine delivery system (ENDS) use among high school students from 2017 to 2019 appear to be associated with the increasing popularity of the ENDS device JUUL. OBJECTIVE: We employed a content analysis approach in conjunction with natural language processing methods using Twitter data to understand salient themes regarding JUUL use on Twitter, sentiment towards JUUL, and underage JUUL use. METHODS: Between July 2018 and August 2019, 11,556 unique tweets containing a JUUL-related keyword were collected. We manually annotated 4000 tweets for JUUL-related themes of use and sentiment. We used 3 machine learning algorithms to classify positive and negative JUUL sentiments as well as underage JUUL mentions. RESULTS: Of the annotated tweets, 78.80% (3152/4000) contained a specific mention of JUUL. Only 1.43% (45/3152) of tweets mentioned using JUUL as a method of smoking cessation, and only 6.85% (216/3152) of tweets mentioned the potential health effects of JUUL use. Of the machine learning methods used, the random forest classifier was the best performing algorithm among all 3 classification tasks (ie, positive sentiment, negative sentiment, and underage JUUL mentions). CONCLUSIONS: Our findings suggest that a vast majority of Twitter users are not using JUUL to aid in smoking cessation nor do they mention the potential health benefits or detriments of JUUL use. Using machine learning algorithms to identify tweets containing underage JUUL mentions can support the timely surveillance of JUUL habits and opinions, further assisting youth-targeted public health intervention strategies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".