Education
Ph.D., Communication (Computational Social Science) 2026 University of Pennsylvania Dissertation: Leveraging LLMs to Evaluate Topics, Misinformation, and Toxicity on Political Podcasts
Master of Science, Statistics and Data Science 2023 The Wharton School, University of Pennsylvania
Master of Science, Communication Science 2021 University of Amsterdam
Professional Experience
Quantitative UX Researcher Mar – May 2026 Meta — Central Growth
- Updated the “New Connections” off-platform survey, then used Claude Code and OpenAI Codex to modernize the analysis, building automated longitudinal workflows across previously siloed survey waves
- Designed a quantitative on-platform Friending Intent survey, with results to directly inform the Friending team’s decision to update Facebook’s People You May Know (PYMK) algorithm
- Smoke-tested the uxr-toolkit research infrastructure (Claude Code slash command), helping to design quantitative research workflows that could drive efficiency gains across Meta’s UXR Org
- Helped build and deploy multiple internal AI agents to accelerate research workflows, including a personal knowledge agent (“Second Brain”), a shared team agent (“Team Brain”) for the Central Growth Friending team, and a custom MyClaw instance
Computational Research Fellow Sep 2021 – Mar 2026 University of Pennsylvania
- Collaborated with Dr. Yphtach Lelkes and Dr. Duncan J. Watts on projects investigating the influence of news media and social media on human behavior
- Designed and executed large-scale quantitative studies including surveys, behavioral experiments, and NLP-based analysis to understand how users interact with media, AI systems, and digital platforms
- Built AI-powered measurement pipelines analyzing over 28,000 podcast episodes and 46.7 million social media posts, delivering findings to interdisciplinary research teams and public-facing stakeholders
- Shipped a public-facing research product (mediabiasdetector.seas.upenn.edu)
Co-Instructor, Modern Data Mining (PhD Level) Jul 2022 – Mar 2026 The Wharton School, University of Pennsylvania
- Taught PhD-level machine learning covering LLMs, neural networks, and ensemble methods; translated complex statistical concepts for technical and non-technical audiences
Selected Publications
Fasching, N. & Lelkes, Y. (2025). Model-Dependent Moderation: Inconsistencies in Hate Speech Detection Across LLM-based Systems. Findings of ACL 2025.
Fasching, N., Iyengar, S., Lelkes, Y., & Westwood, S. J. (2024). Persistent Polarization: The Unexpected Durability of Political Animosity Around US Elections. Science Advances, 10(36).
Fasching, N. & Lelkes, Y. (2024). Ancestral Kinship and the Origins of Ideology. British Journal of Political Science.
Fasching, N., Arceneaux, K., & Bakker, B. N. (2024). Inconsistent and Very Weak Evidence for a Direct Association Between Childhood Personality and Adult Ideology. Journal of Personality, 92(4).
Pangakis, N., Wolken, S., & Fasching, N. (2023). Automated Annotation with Generative AI Requires Validation. arXiv:2306.00176.
Technical Skills
Research Methods: Survey design and fielding, experimental design, A/B testing, causal inference (ITS, DiD, RDD), behavioral data analysis, mixed methods
Statistical Analysis: Regression (linear, logistic, multilevel), SEM, factor analysis, time-series analysis, Bayesian methods
Programming Languages: Python (Expert), R (Expert), SQL (Expert), JavaScript (Proficient)
Data Processing: Pandas, NumPy, PySpark, PyArrow, dplyr/tidyverse
AI Coding & Agent Tools: Claude Code, OpenAI Codex, agent orchestration (OpenClaw, Hermes)
Platforms: AWS, Microsoft Azure, Google Colab, Posit Workbench, Git/GitHub