Joan C. Timoneda
Computer Science · Purdue University West Lafayette
Publications
40
Citations
346
Est. group size
—
Recurring co-author estimate
Active years
19
Publishing since 2008
Joan C. Timoneda works at the intersection of political science and computational text analysis, studying how authoritarian leaders consolidate power and how democratically elected leaders may undermine democratic norms. A significant part of the recent work applies natural language processing and large language models (LLMs) to analyze political and social text, including detecting bias, ideology, and racist language in machine-generated or human-written content. This combines substantive political science questions with methodological contributions to computational text analysis.
Publication output has grown markedly since 2023, with a dip in earlier years (2019, 2022) followed by a strong, steady increase through 2024-2026.
Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026
- Rolling Memory: A New Approach to Annotation with Generative LLMs in Social and Political Research
Chinese Political Science Review · 2026
- Machines Do See Color: Using LLMs to Classify Overt and Covert Racism in Text
Sociological Methods & Research · 2026
- Preregistration — Contextual Alignment Study: A Cross-Developer Study of LLM Behavior on Contested Topics (frozen instrument, git commit 3f8912c)
Zenodo (CERN European Organization for Nuclear Research) · 2026
- Preregistration — Contextual Alignment Study: A Cross-Developer Study of LLM Behavior on Contested Topics (frozen instrument, git commit 3de2a88)
Zenodo (CERN European Organization for Nuclear Research) · 2026
- Preregistration — Contextual Alignment Study: A Cross-Developer Study of LLM Behavior on Contested Topics (frozen instrument, git commit 6e9a95a)
Zenodo (CERN European Organization for Nuclear Research) · 2026
- Preregistration — Contextual Alignment Study: A Cross-Developer Study of LLM Behavior on Contested Topics (frozen instrument, git commit 6e9a95a)
Zenodo (CERN European Organization for Nuclear Research) · 2026
- Can Social Media Help Incumbents Subvert Democracy?
Politics & Society · 2025
- Behind the mask: Random and selective masking in transformer models applied to specialized social science texts
PLoS ONE · 2025
- The trajectories of personalization: how dictators accumulate power over time
Democratization · 2025
- Taking Justices' Legal Preferences Seriously (And Locating Opinions in Policy Space)
SSRN Electronic Journal · 2025
- Ways out of Authoritarianism
Oxford University Press eBooks · 2025
- Is ChatGPT conservative or liberal? A novel approach to assess ideological stances and biases in generative LLMs
Political Science Research and Methods · 2025
- BERT, RoBERTa, or DeBERTa? Comparing Performance Across Transformers Models in Political Science Text
The Journal of Politics · 2024
- The personalization of power in dictatorships
Edward Elgar Publishing eBooks · 2024
- Revisiting the Personalism and Economic Performance Debate: Do All Personalist Dictators Produce Worse Economic Outcomes?
Political Studies Review · 2024
- Harvard Dataverse×9
- Zenodo (CERN European Organization for Nuclear Research)×4
- PLoS ONE×3
- SSRN Electronic Journal×3
- arXiv (Cornell University)×2
- Rajkumar Pujari
Computer Science · Purdue University West Lafayette
- Dan Goldwasser
Computer Science · Purdue University West Lafayette
- Divyanshu Daiya
Computer Science · Purdue University West Lafayette
- Daniel Dakota
Computer Science · Indiana University
- Haining Wang
Computer Science · Indiana University
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 20, 2026.
Claim or correct this profile