Ilya Ilyankou

PhD candidate at UCL researching spatial information behaviour and responsible GeoAI

I am a PhD candidate at UCL’s SpaceTimeLab, supervised by Dr James Haworth and Dr Stefano Cavazzi. My research is funded by UKRI (EPSRC) and Ordnance Survey (OS).

I study how people communicate about place: what they ask, how they ask it, and what this reveals about human spatial information behaviour at scale. I work at the intersection of GeoAI, NLP, and HCI, using query logs and conversational AI datasets to characterise spatial information needs across interfaces. I’m particularly interested in subjective spatial questions – those that go beyond what deterministic GIS can answer, and expose the gap between place as data and place as lived experience.

I am a co-founder and CTO of Safest Way, a Geovation-backed startup developing safety-focused pedestrian navigation. Read about it on BBC News, The Standard, or in The Conversation .

Selected Publications (all publications →)

Conversational AI query classification BritCHI 2026 (accepted)
Conversational Interfaces Reshape What People Ask of Place
GitHub
Ilya Ilyankou, Stefano Cavazzi, James Haworth
[Chatbot users' most distinctively conversational geospatial behaviour is asking the system to write place-grounded text and plan trips, not to retrieve facts.]
Stacked bar chart - Lens composition by form PLATIAL'26 (accepted)
Place Distortion Begins in the Prompt
GitHub
Ilya Ilyankou, Stefano Cavazzi, James Haworth
[The kind of place-writing people ask chatbots for (e.g. joke, review, report about a place) relates to whether the result idealises, stigmatises, or stays neutral; bias starts with the request, not just the answer.]
Web search query classification COSIT 2026 (accepted)
Much of Geospatial Web Search Is Beyond Traditional GIS
arXiv GitHub 🤗 HuggingFace
Ilya Ilyankou, Stefano Cavazzi, James Haworth
[People ask the web about place far more than we thought, and most of it is practical lookups (costs, hours, contact details, weather, etc.) that GIS isn't traditionally built to answer.]
Clip the Landscape landscape image examples Remote Sensing Applications: Society and Environment (2026)
CLIP the Landscape: Automated Tagging of Crowdsourced Landscape Images
RSE:SE Journal GitHub arXiv
Ilya Ilyankou, Natchapon Jongwiriyanurak, Tao Cheng, James Haworth
[What you see isn't always what gets tagged. A CLIP-based classifier combining image, location, and title embeddings to predict geographic context tags from landscape photos, improving spatial understanding in data-sparse regions.]
Quantifying Geospatial paper Figure 2 SIGSPATIAL'24
Quantifying Geospatial in the Common Crawl Corpus
ACM DL Proceedings arXiv
Ilya Ilyankou, Meihui Wang, Stefano Cavazzi, James Haworth
[Nearly one in five Common Crawl documents contains geospatial information, offering a quantitative basis for understanding why LLMs develop spatial reasoning capabilities.]
CC-GPX Figure 1 (multimodal dataset entry example) SIGSPATIAL'24
CC-GPX: Extracting High-Quality Annotated Geospatial Data from Common Crawl
ACM DL Proceedings GitHub arXiv
Ilya Ilyankou, Meihui Wang, Stefano Cavazzi, James Haworth
[A pipeline to extract paired GPX tracks and human-written descriptions from Common Crawl, yielding a multimodal dataset of 1,416 real outdoor routes for geospatial and NLP research.]

See the full publications list for all papers, including as co-author.

Professional experience

  • Intern (Responsible AI Team), Nokia Bell Labs (summer 2026)

  • Intern (Data-Centric Engineering), The Alan Turing Institute (autumn 2025)

  • Data engineer, Geolytix (2022–2025)

  • Full-stack developer, CTData Collaborative (2018–2022)

Teaching

As a postgraduate teaching assistant at UCL (2024–25) and lab demonstrator at Birkbeck (2025–26), I have supported modules in geospatial programming, spatial analysis, and data analytics.

Education

  • PhD in Spatial Information Behaviour and Responsible GeoAI – University College London (UCL), 2023–2027

  • MSc in Geographic Information Science (Distinction) – University of Leeds, 2019–2022

  • BSc in Computer Science and Studio Arts (summa cum laude, Phi Beta Kappa) – Trinity College (Connecticut), 2014–2018

  • Worcester College, University of Oxford – Visiting student focusing on machine learning and game theory, 2016–2017

Hands-On Data Visualization

Hands-On Data Visualization: Interactive Storytelling from Spreadsheets to Code (O’Reilly), co-authored with Jack Dougherty. Available open-access in English, and translated into Korean and Traditional Chinese.

Since 2022, all royalties (currently over $5,000) have been donated to humanitarian relief efforts in Ukraine, most recently to The HALO Trust.

Hands-On Data Visualization book cover