Computational social scientist and independent researcher.
I’m a computer scientist by training, have a PhD in computational linguistics and AI, and worked as a Research Scientist for over 10 years at Facebook/Meta doing data science and computational science research.
I am driven by a methodological curiosity (my curiosity is not methodological, I am curious about methods). I like finding ways to make sense of complex data.
I’ve worked on topics from international migration to network formation, social capital, and personal naming practices.
I am a co-founder of the data visualization collective Çilek Ağacı.
Notes
The effect of zodiac signs on LLM response diversity
Large language models tend to collapse into a narrow set of predictable outputs when prompted multiple times with the same question – a phenomenon known as mode collapse. This matters for applications like brainstorming and creative writing where we want to sample a range of possibilities. In this note, I share results from a kitchen-table experiment: I prompted Claude models with different zodiac signs and Myers-Briggs personality types to see if persona prompts could increase output diversity. My hypothesis is that these persona types are: ...
Featured Work
Facebook Movement Range Maps
I created a privacy-preserving human mobility dataset during the early COVID-19 pandemic, utilizing differential privacy technique to ensure the privacy of indivudal-level data. The dataset, Fadebook/Meta's most-downloaded one on the Humanitarian Data Exchange platform, informed policy experts and decision makers on the efficacy of the COVID measures. It also helped researchers across the world answer questions on the effect of physical distancing and lockdown policies on public health outcomes, and how societies respond to crises such as emergence of bike lanes during COVID in Europe.
Turkish Election Analyses
At Çilek Ağacı, we have analyzed and visualized pretty much all of the Turkish elections and referenda in the last decade and a half. Check them out here.