David Graus
Assistant Professor IR & NLP · Lab Manager ICAI OpenGov Lab
I work at the Institute for Logic, Language and Computation (ILLC) at the University of Amsterdam, where I lead the ICAI OpenGov Lab on AI for open government information. My research and teaching focus on information retrieval, natural language processing, responsible and transparent AI, and improving access to public-sector information. Outside of work I built Zwaailicht.nl, a hobby project — inspired by my IR and NLP research — that collects Dutch emergency-services (P2000) messages and makes them searchable and mappable in real time. For publications, talks, and projects, visit graus.nu.
Contact & Office
Office L6.37, LAB42
Address Science Park 900, 1098 XG Amsterdam, NL
Email d.p.graus@uva.nl
Profiles & Links
Research & Teaching
After a BA in media studies and some years as a science editor for public broadcaster NTR, I did a PhD in information retrieval at the IRLab, University of Amsterdam, on semantic search and entity retrieval in digital traces. That was followed by eight years in industry building search and recommender systems at scale — for news at FD Mediagroep and for the labor market at Randstad — before returning to academia in 2025. That industry stretch is what informs my current work: I've seen where fairness and accountability actually bite in deployed systems, and I bring those questions back into research on IR, NLP, and open government.
I currently teach AI in Society: Safety, Regulation, Fairness (BSc Artificial Intelligence) and Reflection on the Digital Culture (BSc Information Science), both on the societal, regulatory, and ethical dimensions of AI and digital platforms. I supervise two PhD candidates in the ICAI OpenGov Lab: Maik Larooij, on conversational search and retrieval over open government collections, and Damiaan Reijnaers, on explainable NLP for active disclosure.
Selected Projects
WooZM
Search engine for Dutch open government data. Indexes more than 8 million documents across 800+ Dutch public bodies; its data also serves as training data for GPT-NL. Formerly WooGLe, rebranded in 2026.
WooPush
Research project on proactively surfacing relevant local-government information to citizens, developed with several student contributors.
Zwaailicht.nl
A hobby project I built and maintain solo, inspired by my IR and NLP research: a live map and AI-summarized context for Dutch emergency-services (P2000) dispatch messages, from antenna and Raspberry Pi through geocoding, clustering, and LLM summarization, to web and native apps. Privacy-by-design — no cookies, no tracking.
Publications
Selection from 45+ publications (2012–2026). Full list at graus.nu/publications and on Google Scholar.
General public
- 2021Forget the Trolley Problem; Pragmatic and Fair AI in the Real World. TowardsDataScience. Selected as an editors' pick.
- 2016D. Graus, M. de Rijke. Wij zijn racisten, daarom Google ook. NRC Handelsblad.
Peer-reviewed articles
- 2026D. Graus. From Legal Text to Executable Decision Models. International Conference on Artificial Intelligence and Law (ICAIL), Singapore.
- 2026A. Parfenova, D. Graus, J. Pfeffer. From Quotes to Concepts: Axial Coding of Political Debates with Ensemble LMs. Findings of ECIR, Delft, NL.
- 2024A. Fabris, N. Baranowska, M. J. Dennis, D. Graus, P. Hacker, J. Saldivar, F. Z. Borgesius, A. J. Biega. Fairness and Bias in Algorithmic Hiring: a Multidisciplinary Survey. ACM Transactions on Information Systems (TOIS).
- 2022A. M. Arafan, D. Graus, F. P. Santos, E. Beauxis-Aussalet. End-to-End Bias Mitigation in Candidate Recommender Systems with Fairness Gates. RecSys in HR Workshop, ACM RecSys.
- 2021D. Lavi, V. Medentsiy, D. Graus. conSultantBERT: Fine-tuned Siamese Sentence-BERT for Matching Jobs and Job Seekers. RecSys in HR Workshop, ACM RecSys.
- 2020F. Lu, A. Dumitrache, D. Graus. Beyond Optimizing for Clicks: Incorporating Editorial Values in News Recommendation. UMAP.
- 2020O. Berlage, K.-M. Lux, D. Graus. Improving automated segmentation of radio shows with audio embeddings. ICASSP, Barcelona.
- 2018D. Graus, D. Odijk, M. de Rijke. The Birth of Collective Memories: Analyzing Emerging Entities in Text Streams. JASIST.
- 2016D. Graus, P. N. Bennett, R. White, E. Horvitz. Analyzing and Predicting Task Reminders. UMAP, Halifax. Best Student Paper Award.
- 2016D. Graus, E. Tsagkias, W. Weerkamp, E. Meij, M. de Rijke. Dynamic Collective Entity Representations for Entity Ranking. WSDM, San Francisco.
- 2014D. Graus, D. van Dijk, E. Tsagkias, W. Weerkamp, M. de Rijke. Recipient Recommendation in Enterprises using Communication Graphs and Email Content. SIGIR.