Search Articles

View query in Help articles search

Search Results (1 to 5 of 5 Results)

Download search results: CSV END BibTex RIS


Classification of Twitter Vaping Discourse Using BERTweet: Comparative Deep Learning Study

Classification of Twitter Vaping Discourse Using BERTweet: Comparative Deep Learning Study

First proposed by Colditz et al [6], transformers use a self-attention mechanism to capture what aspects of a sequence are important in a series of tokens. In simple terms, self-attention mechanisms aim to create real natural language understanding in machines. In 2018, Google AI Language released the Bidirectional Encoder Representations from Transformers (BERT) model, which improves upon the original transformer model by learning token representations in both directions [7].

William Baker, Jason B Colditz, Page D Dobbs, Huy Mai, Shyam Visweswaran, Justin Zhan, Brian A Primack

JMIR Med Inform 2022;10(7):e33678

Discussions and Misinformation About Electronic Nicotine Delivery Systems and COVID-19: Qualitative Analysis of Twitter Content

Discussions and Misinformation About Electronic Nicotine Delivery Systems and COVID-19: Qualitative Analysis of Twitter Content

Fewer (n=59, 3.1%) mentioned starting or continuing ENDS because of the pandemic (eg, “corona got me thinkin bout my health so i got a juul for in b/w cigs”) and the perceived health benefits of nicotine (eg, “YOU NEED TO VAPE. Nicotine users are at a lower risk of developing COVID-19 symptoms...”). Finally, 33 (1.7%) tweets mentioned switching from traditional cigarettes to ENDS, with all tweets in this coding category containing the theme of ENDS being a safer alternative to cigarette smoking.

Jaime E Sidani, Beth Hoffman, Jason B Colditz, Riley Wolynn, Lily Hsiao, Kar-Hai Chu, Jason J Rose, Ariel Shensa, Esa Davis, Brian Primack

JMIR Form Res 2022;6(4):e26335