Ph.D. Candidate · Computer Science · Northeastern University

Levi Kaplan

I study algorithmic discrimination and fairness in social media platforms — building auditing tools that make opaque recommendation systems legible and accountable.

Levi Kaplan
Scroll

My research investigates algorithmic discrimination, fairness, and bias in social media platforms and other socio-technical systems.

I conduct audits to measure bias present in social media algorithms and build tools to collect, process, and analyze data for fairness auditing. I am motivated by the opacity of recommendation systems and the propensity for harm they can cause. Our work has led to reporting in the popular press and concrete legislative change.

I am advised by Prof. Alan Mislove at Northeastern University. I recently completed a research internship at New York University working with Prof. Damon McCoy.

Algorithm Auditing Algorithmic Fairness Social Media Ad Targeting Measurement

Selected Work

  1. 2024

    PhD Symposium · The Web Conference

    Comprehensively Auditing the TikTok Mobile App

    Levi Kaplan, Piotr Sapiezynski

  2. 2024

    Computer Supported Cooperative Work

    On the Use of Proxies in Political Ad Targeting

    Piotr Sapiezynski, Levi Kaplan, Alan Mislove, Aleksandra Korolova

  3. 2024

    Management Science

    Data Deserts and Black Boxes: The Impact of Socio-Economic Status on Consumer Profiling

    Nico Neumann, Catherine E. Tucker, Levi Kaplan, Piotr Sapiezynski, Alan Mislove

  4. 2022

    Internet Measurement Conference

    Measurement and Analysis of Implied Identity in Ad Delivery Optimization

    Levi Kaplan, Nicole Gerzon, Alan Mislove, Piotr Sapiezynski

    Best Paper Award
  5. 2022

    Artificial Intelligence, Ethics, and Society

    Algorithms that "Don't See Color": Measuring Biases in Lookalike and Special Ad Audiences

    Piotr Sapiezynski, Avijit Ghosh, Levi Kaplan, Aaron Rieke, Alan Mislove

    Runner-Up, Best Student Paper
  • Best Paper Award IMC 2022 · Measurement And Analysis of Implied Identity in Ad Delivery Optimization
  • Runner-Up, Best Student Paper ConPro 2022 · Algorithms that "Don't See Color"
  • ICWSM2026
  • The Web Conference (sub-reviewer)2025
  • IMC (shadow PC)2025
  • IC²S²2025