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 Experiment Videos

Assessing Behavioral Stages From Social Media Data.

Jason Liu1, Elissa R Weitzman2, Rumi Chunara3

  • 1University of Waterloo.

CSCW : Proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work
|October 17, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Bodyweight and Weightlifting Exercise Injury Burden: National Analysis from 2014 to 2023.

Sports medicine international open·2026
Same author

The importance of clinical context in evaluating algorithmic fairness: insights from a medication adherence prediction algorithm.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Participant Attrition Associated With Longitudinal Use of Safety Flag Protocols in Adolescent Substance Use Research.

Substance use & addiction journal·2026
Same author

Development, structure, and implementation of cardiometabolic clinics in the United States, with a focus on comprehensive patient care.

American journal of preventive cardiology·2026
Same author

Surgical Treatment of Accessory Mitral Valve Tissue in a Toddler.

Annals of thoracic surgery short reports·2026
Same author

Patient reported outcome measures in intra-peritoneal adhesive disease: a scoping review.

Techniques in coloproctology·2026
Same journal

Investigating the Role of Situational Disruptors in Engagement with Digital Mental Health Tools.

CSCW : proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work·2026
Same journal

Safe Enough to Share: Setting the Dementia Agenda Online.

CSCW : proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work·2020
Same journal

MoodLight: Exploring Personal and Social Implications of Ambient Display of Biosensor Data.

CSCW : proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work·2018
Same journal

Automatic Archiving versus Default Deletion: What Snapchat Tells Us About Ephemerality in Design.

CSCW : proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work·2018
Same journal

Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions.

CSCW : proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work·2018
Same journal

Computational Approaches Toward Integrating Quantified Self Sensing and Social Media.

CSCW : proceedings of the Conference on Computer-Supported Cooperative Work. Conference on Computer-Supported Cooperative Work·2017
See all related articles

This study uses social media data and machine learning to track health behavior stages in real-time. This approach enhances psychological theories and informs health policy by analyzing dynamic daily actions.

Area of Science:

  • Psychology
  • Social Computing
  • Computational Social Science

Background:

  • Health behavior change theories propose discrete stages.
  • Social media generates vast, dynamic data on individual actions.
  • Understanding real-time behavior is crucial for health.

Purpose of the Study:

  • To leverage social media data for high-resolution identification of health behavior stages.
  • To integrate psychological theory with social computing methods.
  • To explore temporal patterns in behavior stages for public health insights.

Main Methods:

  • Developed a hierarchical classification model for Twitter data.
  • Utilized machine learning and domain knowledge.
  • Analyzed temporal patterns of behavior stages, using alcohol consumption as a case study.
Keywords:
H.3.3. Information Storage and RetrievalH.5.m. Information Interfaces and Presentation (e.g., HCI)Information Storage and RetrievalMiscellaneousbehaviorhealthhierarchical classificationnatural language processingsocial media

Related Experiment Videos

Main Results:

  • Successfully resolved behavior stages (e.g., planning, engaging, reflecting on drinking) at high temporal resolution.
  • Identified distinct temporal patterns in behavior stages.
  • Compared findings with known seasonal trends.

Conclusions:

  • Social media data offers a powerful tool for advancing psychological theories of behavior change.
  • High-frequency detection of behavior stages has significant implications for health policy and interventions.
  • Dynamic, real-world actions captured via social media provide novel insights into health behaviors.