Identifying substance use risk based on deep neural networks and Instagram social media data
Open Access
- 24 October 2018
- journal article
- research article
- Published by Springer Science and Business Media LLC in Neuropsychopharmacology
- Vol. 44 (3), 487-494
- https://doi.org/10.1038/s41386-018-0247-x
Abstract
Social media may provide new insight into our understanding of substance use and addiction. In this study, we developed a deep-learning method to automatically classify individuals’ risk for alcohol, tobacco, and drug use based on the content from their Instagram profiles. In total, 2287 active Instagram users participated in the study. Deep convolutional neural networks for images and long short-term memory (LSTM) for text were used to extract predictive features from these data for risk assessment. The evaluation of our approach on a held-out test set of 228 individuals showed that among the substances we evaluated, our method could estimate the risk of alcohol abuse with statistical significance. These results are the first to suggest that deep-learning approaches applied to social media data can be used to identify potential substance use risk behavior, such as alcohol use. Utilization of automated estimation techniques can provide new insights for the next generation of population-level risk assessment and intervention delivery.Funding Information
- U.S. Department of Health & Human Services | NIH | National Institute on Drug Abuse (P30DA029926, P30DA029926)
- The Office of Provost at Dartmouth College
This publication has 32 references indexed in Scilit:
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- The Prescription Opioid and Heroin Crisis: A Public Health Approach to an Epidemic of AddictionAnnual Review of Public Health, 2015
- Peer Influences: The Impact of Online and Offline Friendship Networks on Adolescent Smoking and Alcohol UseJournal of Adolescent Health, 2014
- Permissive Norms and Young Adults’ Alcohol and Marijuana Use: The Role of Online CommunitiesJournal of Studies on Alcohol and Drugs, 2012
- Image and video disclosure of substance use on social media websitesComputers in Human Behavior, 2010
- The Preventable Causes of Death in the United States: Comparative Risk Assessment of Dietary, Lifestyle, and Metabolic Risk FactorsPLoS Medicine, 2009
- Learning long‐range vision for autonomous off‐road drivingJournal of Field Robotics, 2009
- The Alcohol, Smoking and Substance Involvement Screening Test (ASSIST): development, reliability and feasibilityAddiction, 2002
- Interpersonal factors and post‐treatment drinking and subjective wellbeingAddiction, 1997
- Long Short-Term MemoryNeural Computation, 1997