Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Statistical Methods for Analyzing Epidemiological Data01:25

Statistical Methods for Analyzing Epidemiological Data

1.3K
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
1.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Cognitive and affective neurodevelopment in youth exposed to deprivation and threat.

bioRxiv : the preprint server for biology·2026
Same author

Pathways between parental monitoring and adolescent e-cigarette use: The role of parent-child internalizing and externalizing discrepancies in a predominately Hispanic/Latino(a) sample.

Translational issues in psychological science·2026
Same author

Emotion dysregulation and dissociation mediate the association between alexithymia and depressive symptoms in individuals with alcohol use disorder.

Alcohol and alcoholism (Oxford, Oxfordshire)·2026
Same author

Beyond the family: Peer and neighborhood contexts buffer the effects of childhood threat and deprivation on adolescent functioning.

Child abuse & neglect·2026
Same author

Acculturation Gap Conflict and Self-Control Mediate the Association Between Negative Affect and Sleep Problems for Hispanic/Latino(a) Adolescents.

International journal of environmental research and public health·2025
Same author

Working memory-related brain activations and deactivations linked with adolescent substance use via alexithymia.

Developmental cognitive neuroscience·2025

Related Experiment Video

Updated: May 5, 2026

A Microcontroller Operated Device for the Generation of Liquid Extracts from Conventional Cigarette Smoke and Electronic Cigarette Aerosol
09:30

A Microcontroller Operated Device for the Generation of Liquid Extracts from Conventional Cigarette Smoke and Electronic Cigarette Aerosol

Published on: January 18, 2018

8.4K

The Use of Machine Learning to Predict Offline Adolescent e-Cigarette Use: a Proof-of-Concept.

Julie V Cristello1,2,3, Krzysztof Bogusz4, Elisa M Trucco5,6,7

  • 1Center for Alcohol and Addiction Studies, School of Public Health, Brown University, 121 S Main Street, Providence, RI, 02903, USA. Julie_cristello@brown.edu.

Prevention Science : the Official Journal of the Society for Prevention Research
|May 4, 2026
PubMed
Summary

Researchers used machine learning to analyze Instagram data, successfully predicting adolescent e-cigarette use with 71% accuracy. This method offers a novel approach for identifying at-risk youth.

Keywords:
AdolescenceE-cigarette useMachine learningSocial media

More Related Videos

Generation of Electronic Cigarette Aerosol by a Third-Generation Machine-Vaping Device: Application to Toxicological Studies
08:39

Generation of Electronic Cigarette Aerosol by a Third-Generation Machine-Vaping Device: Application to Toxicological Studies

Published on: August 25, 2018

29.0K

Related Experiment Videos

Last Updated: May 5, 2026

A Microcontroller Operated Device for the Generation of Liquid Extracts from Conventional Cigarette Smoke and Electronic Cigarette Aerosol
09:30

A Microcontroller Operated Device for the Generation of Liquid Extracts from Conventional Cigarette Smoke and Electronic Cigarette Aerosol

Published on: January 18, 2018

8.4K
Generation of Electronic Cigarette Aerosol by a Third-Generation Machine-Vaping Device: Application to Toxicological Studies
08:39

Generation of Electronic Cigarette Aerosol by a Third-Generation Machine-Vaping Device: Application to Toxicological Studies

Published on: August 25, 2018

29.0K

Area of Science:

  • Digital health
  • Computational social science
  • Adolescent health

Background:

  • Adolescent e-cigarette use poses public health challenges, necessitating effective identification strategies.
  • Social media analysis offers a potential avenue for predicting substance use, but traditional methods have limitations.
  • Existing research often relies on self-report or manual coding, which can be subjective and resource-intensive.

Purpose of the Study:

  • To develop and evaluate a supervised machine learning algorithm for classifying adolescent e-cigarette use based on Instagram metrics.
  • To identify key Instagram profile features predictive of e-cigarette use among adolescents.
  • To explore the utility of social media data in informing prevention and intervention programs.

Main Methods:

  • A supervised machine learning model, specifically a classification tree, was developed using Python.
  • Instagram metrics (followers, following, likes, posts, messages) were extracted from participant data.
  • Participant e-cigarette use was assessed via self-report, and data was split for model training and testing.

Main Results:

  • The final machine learning model achieved 71% accuracy in detecting adolescent e-cigarette use.
  • Three Instagram features—number of followers, number of liked posts, and number of messages—were identified as significant predictors.
  • The model's performance was comparable to methods used in other clinical populations.

Conclusions:

  • Supervised machine learning applied to Instagram metrics can effectively predict adolescent e-cigarette use.
  • Social media data provides valuable, objective indicators for identifying at-risk youth.
  • Findings support the use of social media analytics for targeted public health interventions and policy development.