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

Measuring human capital with social media data and machine learning.

Martina Jakob1,2, Sebastian Heinrich3

  • 1Department of Economics, University of Zurich, Zurich, Switzerland. martina.jakob@econ.uzh.ch.

Scientific Reports
|June 4, 2026
PubMed
Summary

Related Concept Videos

Social Foundations of Self IV: Self in Digital Communication01:30

Social Foundations of Self IV: Self in Digital Communication

Since the early 2000s, computer-mediated communication (CMC) has grown rapidly, playing a crucial role in self-development. A key distinction between CMC and real-life interactions is the lack of a physically present partner. This absence makes non-verbal cues such as facial expressions, body language, and paralinguistic signals unavailable in CMC platforms like email, instant messaging, or social media. The lack of these cues can create ambiguity and complicate how feedback is interpreted.The...

You might also read

Related Articles

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

Sort by
Same author

Dislodgement forces and cost effectiveness of prehospital securement of peripheral intravenous catheters on moist skin: a randomized controlled clinical trial in healthy volunteers.

European journal of trauma and emergency surgery : official publication of the European Trauma Society·2026
Same author

Motivational aspects among MEDical Students to Participate as first ResPONDer in out-of-hospital cardiac arrest (MEDSPOND): a pre-post educational intervention study.

BMC medical education·2026
Same author

Major medical events in patients with acute coronary syndrome during helicopter emergency medical service operations.

BMC emergency medicine·2025
Same author

Risk Factors for Postoperative Pulmonary Complications in Patients Undergoing Thoracotomy for Indications Other than Primary Lung Cancer Resection: A Multicenter Retrospective Cohort Study from the German Thorax Registry.

Journal of clinical medicine·2025
Same author

Helicopter hoist operations in German mid-range mountains retrospective analysis of incidence, medical characteristics, and mission tactics.

Scandinavian journal of trauma, resuscitation and emergency medicine·2024
Same author

Smart Dairy Farming-The Potential of the Automatic Monitoring of Dairy Cows' Behaviour Using a 360-Degree Camera.

Animals : an open access journal from MDPI·2024

Social media language and user behavior can predict regional educational attainment with up to 70% accuracy. This offers a novel method for tracking human capital where traditional data is scarce.

Area of Science:

  • Social Sciences
  • Computer Science
  • Education

Background:

  • Timely educational attainment data at granular geographic levels is scarce, hindering evidence-based policy.
  • Machine learning with non-traditional data (satellite imagery, mobile records) has improved development indicator measurement, but educational attainment prediction accuracy remains modest.

Purpose of the Study:

  • To investigate the potential of social media language patterns and user behavior for predicting regional educational attainment.
  • To develop and evaluate a machine learning framework utilizing digital communication data for educational outcome assessment.

Main Methods:

  • Leveraged linguistic features, user behavior, and network characteristics from 25 million geolocated tweets in the United States and Mexico.
  • Developed a machine learning framework to analyze social media data for predicting educational attainment levels.
Keywords:
EducationHuman capitalIndicatorsMachine learningNatural language processingSocial media data

Related Experiment Videos

Main Results:

  • Social media data explained up to 70% of the variance in regional educational attainment.
  • The framework performed particularly well in predicting higher education levels.
  • Good predictive performance was maintained even with limited data collection periods.

Conclusions:

  • Digital communication patterns, specifically social media language and behavior, serve as reliable proxies for human capital.
  • This approach offers a promising method for tracking educational outcomes in data-scarce regions globally.
  • The findings highlight the potential of social media analytics for educational policy and research.