Which aesthetics do we associate with gentrification?

StreetSwipe let’s the audience determine if they think a photo of a storefront of bar should be classified as ‘gentrified’. While swiping, different cities, streets, years and neighborhoods will be compared on a live webpage that functions as a scoreboard.

The subjective input of different groups of users will be used to train different computer models that can recognize and, using so-called Generative Adverserial Networks (GAN’s), generate images that are perceived as gentrified and non-gentrified. The dataset as presented in this Wiki-entry is compiled out of StreetView images of several Amsterdam streets and is used to present to users in the web-version of StreetSwipe.net.

‘StreetSwipe’ relates directly to similar research where StreetView images were used together with computer vision to classify if a street was perceived as safe or unsafe. In similar projects, it often remains obscure how the computational models are trained: who gets to decide what is perceived as safe and how is this idea projected as neutral and objective into the future? With this, computation does not merely govern our actions in the present, but constructs a future that best fits its parameters [1].

The aim of StreetSwipe is twofold: the generation of new knowledge that is aimed at researching a perceived state of gentrification through its aesthetics (colours, patterns, objects) and while doing so, to increase understanding of how computational systems are developed, function and implemented.

A first version of StreetSwipe is already developed and functioning. However the coming year new functionalities will be added, more data will be acquired and different communities will be asked to participate in the project.

Aesthetics of Exclusion is a design research project that uses computer vision techniques and machine learning to explore and analyse aesthetical styles that relate to gentrification and processes of (urban) homogenization through large image archives such as (Google) StreetView and Instagram.

It studies the visual signals and patterns of gentrification: an urban phenomenon that entails a decrease of diversity in classes, ethnicities, races, sexualities, languages, and points of view from central city neighbourhoods; and their replacement by more affluent and homogeneous groups. While a lot of research has focused on the socio-economic causes and effects of this process, we view gentrification also a cultural phenomenon: its aesthetics are not only a reflection of, but a central component in these sort of processes.

Machine learning and computation present new opportunities to research ‘the visual’ on a large scale and make it possible to question, explore, and possibly even disrupt the homogenization of the urban fabric. As these processes relate and interact with homogenization in the digital realm, these new research techniques are not only a means to an end, but also an object of study itself.

In this Wiki-entry we will share a tool that automatically saves a screenshot that has been made in Google Streetview under the GPS code of the location and share a dataset of images of the facades of bars/shops/etc. Both have been developed for the project StreetSwipe.

Author : Sjoerd ter Borg - Aesthetics of Exclusion


[1].James Bridle (2018) New Dark Age. Technology and the End of the Future. Verso: London.

  • street_swipe.txt
  • Last modified: 2019/12/18 15:31
  • by waag