A new study has found that gentrification in London boroughs can actually be predicted ahead of time, by analysing the “social diversity” of a given area. If a location or venue is frequented by a varied group of people from different backgrounds and social circles who wouldn’t usually mix, then it is socially diverse, with a higher likelihood of becoming gentrified than more homogeneous, isolated areas.
The report, entitled ‘Measuring Urban Social Diversity Using Interconnected Geo-Social Networks’, was produced by Cambridge in partnership with the University of Birmingham, Queen Mary University of London, and University College London. It was presented at the 23th International World Wide Web Conference in Montreal this week.
“We found that the most socially cohesive and homogeneous areas tend to be either very wealthy or very poor, but neighbourhoods with both high social diversity and high deprivation are the ones which are currently undergoing processes of gentrification,” writes lead author Desislava Hristova.
Researchers examined over 500,000 social posts and check-ins from 37,000 users in 2010, spread across over 42,000 locations in London. From this data they were able to identify four central metrics which function as “good predictors of gentrification when measured through indices of deprivation”:
- Brokerage: How likely people are to visit somewhere alone, as opposed to in a group.
- Serendipity: How likely people are to visit a location at the same time.
- Entropy: How diverse the visitors to an area are.
- Homogeneity: How similar the visitors to a location are in terms of characteristics.
Many of the areas which the researchers recognised as having high social diversity back in 2010 are, in fact, now in the process of gentrifying, with Hackney leading the charge; it was ranked as the highest climber in the 2015 UK Index of Multiple Deprivation. Other boroughs analysed in the report include Hammersmith, Tower Hamlets and Lambeth.
While it is usually not common practise to use data social media in population studies, as it denotes affluence and social mobility, Hristova remarks that when it comes to determining whether or not an area is becoming gentrified, this bias actually works to their advantage. “The people that may be causing gentrification are precisely these social media users,” she adds.
The findings of this study will be of particular interest to local authorities and campaigners, as well as to private companies looking to turn social diversity data into value for their consumers. Hristova sees apps which use geo-location and push notifications as a natural fit for these kinds of insights. “It could even be used as a specialised local search engine,” she says. “Whether a place is touristy or quiet, artsy or mainstream, could be integrated into mobile system design to help newcomers or tourists feel like locals.”