Competition 2016: Shortlisted in the category Research

Smelly Maps

University of Turin, 2016
Area Mobility Planning Urban Development Medium Information Visualization Type Research

Researchers have used large quantities of online data to study dynamics in novel ways. Consider the specific case of online networked individuals (e.g., users of Twitter, Instagram, Flickr). Can their social dynamics be used to build better tools for future cities? To answer this question, our research has focused on understanding how people psychologically experience cities. As a result, we have created new mapping tools that leverage senses and emotions, thus complementing the idea of an efficient and predictable smart city, with the ultimate goal of reaching urban happiness. The project presented mixes data mining, urban informatics, and computational social science to show how a creative use of social media and network-generated data can capture the sensorial layers of our cities at scale.

Humans are able to potentially discriminate millions of different odors. Yet, city officials and urban planners deal only with the management of few bad odors. This negative and oversimplified perspective comes from the difficulty of measuring smell at scale: cities are victims of a discipline?s negative perspective. The goal of Smelly Maps is to open up a new stream of research that celebrates the complex smell fragments of our cities, by contributing to the development of a critical voice for the positive and negative roles that smell has to play in the design of a city.

To create the smellscape of a city, first we created a lexicon of smell-related words. We then obtained social media photos geo-referenced in the urban area that matched our lexicon. Depending on where those photos were taken, we mapped the presence of smell categories in each street segment. Smelly Maps illustrates the smellscape of 12 cities around the world, each street is colored with the most characteristic smell in the area, while a click on a street segment shows the entire distribution of smells categories and the corresponding emotional response. In the same direction, we mapped the visual and sonic (Chatty Maps) footprints of a city; maps are available within the initiative.



  • Schifanella, Rossano University of Turin
  • Aiello, Luca Nokia Bell Labs
  • Quercia, Daniele Nokia Bell Labs