MSc thesis topics: The online profile of a city

Cities are complex and highly dynamic. Although some city halls, such as Amstersdam’s, provide quite some data about the city ( ), a lot more data is continuously being collected by online organizations such as Google, TripAdvisor, Twitter, Airbnb or OpenStreetMap. Part of these data originates from user reviews and opinions. Making use of these data potentially offers a snapshot of how citizens and visitors perceive different elements of the urban fabric.

As cities grow and neighbourhoods change, it is hard to track how the different sections of an urban area are currently perceived by the people that participate in activities that take place there. Although finding some information about restaurants and hotels can be easy (the city hall of Amsterdam does provide a list of such businesses) and can help understanding the nature of each neighbourhood, it lacks the perspective of the users, whose perception we are ultimately interested in.

On the other hand, online service companies, such as Google, TripAdvisor or Airbnb, thrive on the opinions these clients share with them. Some of these companies provide access to data with which we can obtain a much richer online profile of a city, allowing a better understanding of how each neighbourhood is perceived.

However, this sort of information is not homogeneously distributed. Some areas may have less information due to a variety of reasons: new establishments, different user profiles or lower flux of people. The question is whether it is possible to relate this sparse source of information, based for instance on online reviews, to more homogeneously distributed data, such as satellite imagery, OpenStreetMap layers or Google Street View images. This would open up the possibility of studying city dynamics beyond the most popular areas and at a higher temporal frequency.


  • Identify the online services that provide information related to the perception of urban elements.
  • Extract this information for the city of Amsterdam to create a functional map of the city.
  • Study how the different data sources relate to each other.


  • Salesses, P., Schechtner, K., & Hidalgo, C. A. The Collaborative Image of The City: Mapping the Inequality of Urban Perception, PLoS One, 2013
  • García-Palomares, J. C., Salas-Olmedo, M. H., Moya-Gómez, B., Condeco-Melhorado, A., & Gutierrez, J. City dynamics through Twitter: Relationships between land use and spatiotemporal demographics, Cities, 2018
  • Dubey, A., Naik, N., Parikh, D., Raskar, R., & Hidalgo, C. A. Deep learning the city: Quantifying urban perception at a global scale, ECCV, 2016


  • Programming skills in Python (or high motivation for learning)
  • Some background in statistics and/or machine learning is an asset.

Theme(s): Modelling & visualisation, Human – space interaction