Using Facebook language to predict and describe excessive alcohol use. (16th May 2022)

• Record Type: Journal Article
• Authors: Jose, Rupa; Matero, Matthew; Sherman, Garrick; Curtis, Brenda; Giorgi, Salvatore; Schwartz, Hansen Andrew; Ungar, Lyle H.
• Is Part Of: Alcoholism. Volume 46:Number 5(2022)
• Page Start: 836
• Page End: 847
• Publication Date: 2022-05-16
• Subjects: excessive alcohol use -- natural language processing -- social media -- subclinical drinking; Alcoholism -- Periodicals; Alcoholism -- Periodicals; Alcoolisme; Electronic journals; Périodique électronique (Descripteur de forme); Ressource Internet (Descripteur de forme); 616.861005
• DOI: 10.1111/acer.14807
• Languages: English
• ISSNs: 0145-6008

Abstract

Abstract: Background: Assessing risk for excessive alcohol use is important for applications ranging from recruitment into research studies to targeted public health messaging. Social media language provides an ecologically embedded source of information for assessing individuals who may be at risk for harmful drinking. Methods: Using data collected on 3664 respondents from the general population, we examine how accurately language used on social media classifies individuals as at‐risk for alcohol problems based on Alcohol Use Disorder Identification Test‐Consumption score benchmarks. Results: We find that social media language is moderately accurate (area under the curve = 0.75) at identifying individuals at risk for alcohol problems (i.e., hazardous drinking/alcohol use disorders) when used with models based on contextual word embeddings. High‐risk alcohol use was predicted by individuals' usage of words related to alcohol, partying, informal expressions, swearing, and anger. Low‐risk alcohol use was predicted by individuals' usage of social, affiliative, and faith‐based words. Conclusions: The use of social media data to study drinking behavior in the general public is promising and could eventually support primary and secondary prevention efforts among Americans whose at‐risk drinking may have otherwise gone "under the radar." Abstract : Using AUDIT‐C scores and Facebook language data from 3, 664 respondents, we assess whether language can be used to classify alcohol risk and discuss linguistic differences by risk status. Findings indicate that models relying on contextual word embeddings are fairly accurate at classifying alcohol risk level and that certain words are associated with high‐risk drinkers ("party", "beer", etc.). Social media language holds promise in the identification, monitoring, and possible treatment of individuals vulnerable to alcohol problems or disorders.