Web scraping · Text analysis · Topic modelling · Urban systems insight
Overview
A data-driven study of how public narratives shape the future of autonomous mobility.
Using Python-based web scraping and topic modelling, this project analyses 680+ public sources to identify the dominant concerns surrounding Connected and Autonomous Vehicles (CAVs), and translates them into system-level insights for urban design and policy.
Developed as part of the Innovate UK CCAV project Synergy.
My Role
- Designed and implemented web scraping workflows (Python, Requests, BeautifulSoup)
- Collected and structured a dataset of 680+ sources (news, blogs, reports)
- Cleaned and prepared unstructured text data for analysis
- Contributed to topic modelling (LDA) interpretation
- Translated outputs into thematic clusters and visual frameworks
Objective
The project focused specifically on identifying concerns within public discourse.
The aim was to:
- Extract concern-related narratives from publicly available sources
- identify recurring patterns in how risks, uncertainties, and challenges are framed
- structure these into coherent themes that can inform design and decision-making
This framing positioned discourse as a signal of friction points in future mobility systems.
Acknowledgements
Developed as part of the Innovate UK CCAV Project Synergy.
Co-authored with:
Solon Solomou · Ulysses Sengupta · Iannis Kotsiopoulos · Rob Hyde