Marijn ten Thij
Psychology · Indiana University
Publications
45
Citations
749
Est. group size
—
Recurring co-author estimate
Active years
15
Publishing since 2012
Marijn ten Thij studies how computational methods can be applied to human behavior and language, spanning topics like detecting misinformation online, analyzing sentiment and emotion in social media, and building privacy-preserving machine learning systems. Recent work combines mental health text analysis (such as identifying cognitive distortion in suicide-prevention chats) with technical research on federated learning, a way of training AI models across multiple parties without sharing raw data. The research bridges psychology, natural language processing, and data science.
Publication activity has been fairly steady over the past several years, averaging about five papers per year with output continuing through 2026.
Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026
- Fair incentive allocation in vertical federated learning using nucleolus
Elsevier eBooks · 2026
- Contributors
Elsevier eBooks · 2026
- HybridFL: A Federated Learning Approach for Financial Crime Detection
arXiv (Cornell University) · 2026
- HybridFL: A Federated Learning Approach for Financial Crime Detection
arXiv (Cornell University) · 2026
- Prevalence of Cognitive Distortion Markers in a Suicide Prevention Chat Service: Mixed Methods Study
JMIR Mental Health · 2026
- Vertical federated learning: a structured literature review
Knowledge and Information Systems · 2025
- VFL-RPS: Relevant Participant Selection in Vertical Federated Learning
2025
- VFL-RPS: Relevant Participant Selection in Vertical Federated Learning
arXiv (Cornell University) · 2025
- Prevalence of cognitive distortion markers in a suicide prevention chat service (Preprint)
2025
- Blocking the information war? Testing the effectiveness of the EU’s censorship of Russian state propaganda among the fringe communities of Western Europe
Internet Policy Review · 2024
- Using the Nucleolus for Incentive Allocation in Vertical Federated Learning
2024
- Debunking and exposing misinformation among fringe communities: Testing source exposure and debunking anti-Ukrainian misinformation among German fringe communities
Harvard Kennedy School Misinformation Review · 2024
- Replication Data for Debunking and exposing misinformation among fringe communities: Testing source exposure and debunking anti-Ukrainian misinformation among German fringe communities.
Research Publications (Maastricht University) · 2024
- IDEM: The IDioms with EMotions Dataset for Emotion Recognition
2024
- Incentive Allocation in Vertical Federated Learning Based on Bankruptcy Problem
arXiv (Cornell University) · 2023
- arXiv (Cornell University)×7
- PLoS ONE×3
- Proceedings of the National Academy of Sciences×2
- Elsevier eBooks×2
- Journal of Medical Internet Research×1
This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.
Last updated Jul 11, 2026.
Claim or correct this profile