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

Enhancing Transparency and Control When Drawing Data-Driven Inferences About Individuals.

Daizhuo Chen1, Samuel P Fraiberger2, Robert Moakler3

  • 11 Columbia Business School , New York, New York.

Big Data
|September 22, 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

Can social media reliably estimate unemployment?

PNAS nexus·2026
Same author

Socioeconomic disparities in mobility behavior during the COVID-19 pandemic in developing countries.

EPJ data science·2025
Same author

The Impact of Cloaking Digital Footprints on User Privacy and Personalization.

Big data·2025
Same author

Long ties, disruptive life events, and economic prosperity.

Proceedings of the National Academy of Sciences of the United States of America·2023
Same author

Predicting food crises using news streams.

Science advances·2023
Same author

Association between COVID-19 outcomes and mask mandates, adherence, and attitudes.

PloS one·2021
Same journal

Explainable Machine Learning-Based Prediction of Postoperative Hypoxemia in Elderly Patients Undergoing General Anesthesia.

Big data·2026
Same journal

Big Data-Driven Video Anomaly Detection Using VideoMAE for Visual Analytics in CCTV Surveillance.

Big data·2026
Same journal

Agentic Artificial Intelligence-Driven Explainable Deep Learning for Deciphering Noncoding Pathogenic Mechanisms of Delirium Through Genomic Big Data Integration.

Big data·2026
Same journal

Personalized Driven Instruction Through Explainable Agentic AI in Multicultural Higher Education Environments.

Big data·2026
Same journal

Big Data-Driven Explainable Agentic AI Decision Frameworks for Enterprise Innovation in FinTech Ecosystems.

Big data·2026
Same journal

An Edge-Enabled Low-Latency Cross-Lingual Speech-to-Text Framework for Efficient Human-Robot Interaction.

Big data·2026
See all related articles

Users can control personal inferences drawn from their online actions on social media. A "cloaking device" allows users to hide specific data, significantly impacting predictive models with minimal effort.

Area of Science:

  • Social Computing
  • Data Privacy
  • Predictive Modeling

Background:

  • Social network sites (SNS) enable fine-grained user data analysis for personal characteristic inference.
  • Increasing attention is given to organizational transparency and user control over data inferences.
  • Online actions, like Facebook
  • Likes
  • are a rich source for predictive modeling.

Purpose of the Study:

  • To investigate user control over personal inferences derived from online actions.
  • To introduce a
  • cloaking device
  • for users to inhibit data use in inference.
  • To analyze the impact of cloaking on inference accuracy and organizational modeling strategies.

Main Methods:

Keywords:
comprehensibilitycontrolinferencepredictive modelingprivacytransparency

Related Experiment Videos

  • Developed a transparency mechanism to identify data driving predictive inferences.
  • Introduced a
  • cloaking device
  • allowing users to block specific data points from inference.
  • Examined the quantity of data needed for effective cloaking and the impact of organizational modeling choices.

Main Results:

  • Users typically need to cloak only a small fraction of their online actions to significantly affect inferences.
  • False-positive inferences are more easily cloaked than true-positive inferences.
  • Organizations can alter modeling behavior to increase the data required for effective user cloaking.

Conclusions:

  • Transparency and user control are achievable for complex, model-driven inferences on social media.
  • Organizations can balance user control by adjusting their predictive modeling approaches.
  • The
  • cloaking device
  • offers a practical tool for enhancing user privacy in data inference.