What makes urban areas lively and safe?
Event details
| Date | 31.10.2016 |
| Hour | 14:15 › 15:15 |
| Speaker |
Bruno Lepri leads the Mobile and Social Computing Lab (MobS) and is vice-responsible of the Complex Data Analytics research line at Bruno Kessler Foundation (Trento, Italy). Bruno is also research affiliate at the MIT Media Lab working with the Human Dynamics group and the MIT Connection Science initiative, where he is one of the researchers contributing to Social Physics. He recently launched an alliance between MIT and FBK on Human Dynamics Observatories. He is also a senior research affiliate of Data-Pop Alliance, the first think-tank on Big Data and Development co-created by the Harvard Humanitarian Initiative, MIT Media Lab, Overseas Development Institute, and Flowminder to promote a people-centered Big Data revolution. He holds a Ph.D. in Computer Science from the University of Trento. His research interests include computational social science, big data and personal data, pervasive and ubiquitous computing, and human behavior understanding. |
| Location | |
| Category | Conferences - Seminars |
Policy makers, urban planners, architects, sociologists, and economists are interested in creating urban areas that are both lively and safe. But are the safety and liveliness of neighborhoods independent characteristics? Or are they just two sides of the same coin?
In my talk, I first discuss our work on verifying the Jane Jacobs's four conditions necessary for the promotion of urban life in the Italian context. We have done so by operationalizing her concepts in new ways: we used mobile phone records to extract a proxy for urban vitality and Web data to extract structural proxies for urban diversity. As Jacobs envisioned, vitality and diversity are intimately linked. Moreover, to paraphrase the Jacobs' four conditions in the Italian context, we might say that active Italian districts have dense concentrations of workers, third places at walking distance, small streets, and historical buildings.
Then, I describe a recent work we did on exploring the connection between the levels of activity and the perception of safety of neighborhoods in two major Italian cities by combining mobile phone data (as a proxy for liveliness) with scores of perceived safety estimated using a Convolutional Neural Network trained on a dataset of Google Street View images scored using a crowdsourced visual perception survey. Our results show that (i) safer looking neighborhoods are more active than what is expected from their population density, employee density, and distance to the city centre; and (ii) that the correlation between appearance of safety and activity is positive, strong, and signicant, for females and people over 50, but negative for people under 30, suggesting that the behavioral impact of perception depends on the demographic of the population. Finally, we use occlusion techniques to identify the urban features that contribute to the appearance of safety, finding that greenery and streets facing windows contribute to a positive appearance of safety. These results suggest that urban appearance modulates levels of human activity and, consequently, a neighborhood's rate of natural surveillance.
In my talk, I first discuss our work on verifying the Jane Jacobs's four conditions necessary for the promotion of urban life in the Italian context. We have done so by operationalizing her concepts in new ways: we used mobile phone records to extract a proxy for urban vitality and Web data to extract structural proxies for urban diversity. As Jacobs envisioned, vitality and diversity are intimately linked. Moreover, to paraphrase the Jacobs' four conditions in the Italian context, we might say that active Italian districts have dense concentrations of workers, third places at walking distance, small streets, and historical buildings.
Then, I describe a recent work we did on exploring the connection between the levels of activity and the perception of safety of neighborhoods in two major Italian cities by combining mobile phone data (as a proxy for liveliness) with scores of perceived safety estimated using a Convolutional Neural Network trained on a dataset of Google Street View images scored using a crowdsourced visual perception survey. Our results show that (i) safer looking neighborhoods are more active than what is expected from their population density, employee density, and distance to the city centre; and (ii) that the correlation between appearance of safety and activity is positive, strong, and signicant, for females and people over 50, but negative for people under 30, suggesting that the behavioral impact of perception depends on the demographic of the population. Finally, we use occlusion techniques to identify the urban features that contribute to the appearance of safety, finding that greenery and streets facing windows contribute to a positive appearance of safety. These results suggest that urban appearance modulates levels of human activity and, consequently, a neighborhood's rate of natural surveillance.
Practical information
- Informed public
- Free