Background: Advances in social technologies offer new tools for large scale data collection and analysis of peer influence and social networks on substance use attitudes and behaviors. Objective: The objective of this study was to determine if text message content can predict alcohol and marijuana use attitudes and behaviors. Methods: Text messages from 91 males ages 18-25 were monitored over a period of 6 months and examined for content related to alcohol and marijuana. Self-report data indicating alcohol and marijuana use attitudes and behaviors were used to determine relationships between text message content, social network structure, and substance use attitudes and behaviors. Results: In total, 23,173 text messages were analyzed with 166 text messages including alcohol related terms and 195 text messages including drug related terms. Individuals who sent text messages related to alcohol use were more likely to have problem alcohol use and positive attitudes toward alcohol use, and individuals who sent text messages related to marijuana use reported higher frequency of marijuana use and more positive attitudes toward marijuana use. Individuals with multiple daily marijuana use were in positions that had less control over network structure. Conclusions: The results of this study indicate that monitoring text message content and social network structure among emerging adult males can potentially predict alcohol and marijuana use attitudes and behaviors. Text message content analysis is a novel technique increasing our understanding of the role of peer influence and social network on substance use attitudes and behaviors.
Keywords: Alcohol; emerging adults; marijuana; social network; text mining.