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.

Exploring changes in temporary abstinence in increasing and higher risk drinkers in England and Dry January participation in users of the Try Dry app in the UK between 2020 and 2021.

BACKGROUND: We looked at changes in the prevalence of increasing and higher risk drinkers reporting a reduction attempt motivated by temporary abstinence and changes in prevalence of use of the official app accompanying Dry January between 2020 vs 2021, following the onset of the COVID-19 pandemic. We also explored potential shifts in the sociodemographic composition of both groups. METHODS: We analysed data from: i) 1863 increasing and higher risk drinkers (defined as ≥ 8 on the AUDIT) responding to a nationally representative survey of adults in England in January and February 2020 and 2021, and ii) 104,598 users of the 'Try Dry' app, the official aid to those participating in Dry January 2020 and 2021 in the UK. We used logistic regression to examine shifts in the prevalence of increasing and higher risk drinkers reporting a reduction attempt motivated by temporary abstinence and explored whether there were shifts in the characteristics of this group in terms of AUDIT score, number of last year reduction attempts, smoking status, living alone, living with children, reducing alcohol consumption due to future health motives, age, sex, and occupational social grade between 2020 and 2021. We used t-tests and chi-squared tests to compare the prevalence of users of the 'Try Dry' app in 2020 and 2021 and examine whether the two groups differed in terms of age and sex. RESULTS: The proportion of increasing and higher risk drinkers reporting a reduction attempt motivated by temporary abstinence increased from 4% in 2020 to 8% in 2021 (OR = 2.07, 95% CI = 1.38-3.11, p < .001) with no changes detected in sociodemographic composition. The number of Try Dry app users in 2021 increased by 34.8% relative to 2020. App users in 2021 were two years older on average [p < .001, d = .02], with a 2% increase in the proportion of female app users [p < .001, vs. < .01]. CONCLUSIONS: Higher participation in Dry January 2021 relative to 2020 indicates increased engagement with a period of temporary abstinence following the COVID-19 related lockdowns in England and the UK, which is positive in the wider context of increasing alcohol consumption throughout the pandemic.