Using Natural Language Processing to Explore "Dry January" Posts on Twitter: Longitudinal Infodemiology Study.

BACKGROUND: Dry January, a temporary alcohol abstinence campaign, encourages individuals to reflect on their relationship with alcohol by temporarily abstaining from consumption during the month of January. Though Dry January has become a global phenomenon, there has been limited investigation into Dry January participants' experiences. One means through which to gain insights into individuals' Dry January-related experiences is by leveraging large-scale social media data (eg, Twitter chatter) to explore and characterize public discourse concerning Dry January. OBJECTIVE: We sought to answer the following questions: (1) What themes are present within a corpus of tweets about Dry January, and is there consistency in the language used to discuss Dry January across multiple years of tweets (2020-2022)? (2) Do unique themes or patterns emerge in Dry January 2021 tweets after the onset of the COVID-19 pandemic? and (3) What is the association with tweet composition (ie, sentiment and human-authored vs bot-authored) and engagement with Dry January tweets? METHODS: We applied natural language processing techniques to a large sample of tweets (n=222,917) containing the term "dry january" or "dryjanuary" posted from December 15 to February 15 across three separate years of participation (2020-2022). Term frequency inverse document frequency, k-means clustering, and principal component analysis were used for data visualization to identify the optimal number of clusters per year. Once data were visualized, we ran interpretation models to afford within-year (or within-cluster) comparisons. Latent Dirichlet allocation topic modeling was used to examine content within each cluster per given year. Valence Aware Dictionary and Sentiment Reasoner sentiment analysis was used to examine affect per cluster per year. The Botometer automated account check was used to determine average bot score per cluster per year. Last, to assess user engagement with Dry January content, we took the average number of likes and retweets per cluster and ran correlations with other outcome variables of interest. RESULTS: We observed several similar topics per year (eg, Dry January resources, Dry January health benefits, updates related to Dry January progress), suggesting relative consistency in Dry January content over time. Although there was overlap in themes across multiple years of tweets, unique themes related to individuals' experiences with alcohol during the midst of the COVID-19 global pandemic were detected in the corpus of tweets from 2021. Also, tweet composition was associated with engagement, including number of likes, retweets, and quote-tweets per post. Bot-dominant clusters had fewer likes, retweets, or quote tweets compared with human-authored clusters. CONCLUSIONS: The findings underscore the utility for using large-scale social media, such as discussions on Twitter, to study drinking reduction attempts and to monitor the ongoing dynamic needs of persons contemplating, preparing for, or actively pursuing attempts to quit or cut down on their drinking.

Assessment of Exclusive, Dual, and Polytobacco E-Cigarette Use and COVID-19 Outcomes Among College Students.

PURPOSE: This study examined current (past 30-day) dual- and polytobacco use patterns and COVID-19 symptomatology, testing, and diagnosis status among college student electronic cigarette (e-cigarette) users. DESIGN: Cross-sectional online questionnaire administered during October-December 2020. SETTING: Four large, U.S. public universities in geographically diverse locations. SAMPLE: College students (N=756) ages 18-24 who reported current e-cigarette use. MEASURES: Current use of e-cigarettes, combustible cigarettes, and cigars, and self-reported COVID-19 symptomatology, testing, and diagnosis status were measured. ANALYSIS: Multivariable logistic regression models accounting for students' demographics, university site, fraternity/sorority membership, and current residence. RESULTS: Over half (53.6%) of students were exclusive e-cigarette users, 20.4% were dual e-cigarette and combustible cigarette users, 4.6% were dual e-cigarette and cigar users, and 21.4% were poly users of e-cigarettes, combustible cigarettes, and cigars. Compared to exclusive e-cigarette users, dual users of e-cigarettes and combustible cigarettes (AOR=2.12, 95%CI=1.05-4.27) and poly users of e-cigarettes, combustible cigarettes, and cigars (AOR=3.70, 95%CI=1.78-7.70) had increased odds of COVID-19 symptomatology, even when accounting for covariates. While current tobacco use groups did not differ based on COVID-19 testing, polytobacco users had significantly increased odds (AOR=2.16, 95%CI=1.11-4.20) of having received a positive COVID-19 diagnosis. CONCLUSION: Given use of two or more tobacco products increased COVID-19-related risks, results underscore the need to prevent dual- and polytobacco use behaviors in college student e-cigarette users.

Concurrent use of e-cigarettes and cannabis and associated COVID-19 symptoms, testing, and diagnosis among student e-cigarette users at four U.S. Universities.

INTRODUCTION: This investigation assessed whether current (past 30-day) electronic cigarette (e-cigarette) and cannabis use was associated with coronavirus disease 2019 (COVID-19) symptomatology, testing, and diagnosis among college student e-cigarette users. METHODS: Participants were 18-26-year-old college student e-cigarette users attending four geographically diverse, large U.S. public universities during October-December 2020 (N = 800). Multivariable logistic regression models explored associations between exclusive e-cigarette use and concurrent e-cigarette and cannabis use and COVID-19 symptoms, testing, and diagnosis. Models controlled for demographics, university site, and current use of combustible cigarettes, cigars, and smokeless tobacco. RESULTS: Over half of student e-cigarette users (52.0%) concurrently used cannabis. Compared to exclusive e-cigarette users, concurrent e-cigarette and cannabis users were 3.53 times more likely (95%CI = 1.96-6.36) to report COVID-19 symptoms, after adjusting for the covariates. Compared to infrequent exclusive e-cigarette users, infrequent concurrent users (AOR = 4.72, 95%CI = 1.31-17.00), intermediate concurrent users (AOR = 5.10, 95%CI = 1.37-18.97), and frequent concurrent users (AOR = 7.44, 95%CI = 2.06-26.84) were at increased odds of reporting COVID-19 symptoms. Compared to exclusive e-cigarette users, concurrent e-cigarette and cannabis users were 1.85 times more likely (95%CI = 1.15-2.98) to report a COVID-19 diagnosis. Intermediate concurrent users (AOR = 2.88, 95%CI = 1.13-7.35) and frequent concurrent users (AOR = 3.22, 95%CI = 1.32-7.87) were at increased odds of reporting a COVID-19 diagnosis, compared to infrequent exclusive e-cigarette users. CONCLUSIONS: Concurrent use of e-cigarettes and cannabis may be an underlying risk factor of COVID-19 symptomatology and diagnosis, with more pronounced odds found among intermediate and frequent users. Results highlight the need to educate students about the impacts of e-cigarette and cannabis use on respiratory, immune, and overall health.