Bot detection paper published in DST

Our paper “Explainable Data-Driven Multi-Filter Framework for Bot Detection in Incentivized Online Surveys” is published in Data Science for Transportation (Vol. 8, Article 21). The paper combines platform signals, browser fingerprinting, timing analysis, and an XGBoost validation model to filter bots out of incentivized survey data. Especially proud of this one — it was led by Andrew Ruger, an REU student I mentored in Summer 2025.