Over a million developers have joined DZone.
{{announcement.body}}
{{announcement.title}}

Using Big Data To Understand The Cultural Wealth Of Cities

DZone's Guide to

Using Big Data To Understand The Cultural Wealth Of Cities

The social media website Flickr was crawled to determine the "cultural capital" of London and New York.

· AI Zone ·
Free Resource

Did you know that 50- 80% of your enterprise business processes can be automated with AssistEdge?  Identify processes, deploy bots and scale effortlessly with AssistEdge.

Cities are inherently complex places, and as such, it can be difficult to fully explain their successes or failures. French anthropologist, Pierre Bourdieu believed that cultural capital, such as education, intellect, and knowledge play a crucial role in individual success. Might the same apply to cities?

A recent study led by the University of Cambridge attempted to find out. The task was made especially difficult by the challenge inherent in actually measuring cultural capital. The team believed they found a way that revolved around the social networking site Flickr.

The website was crawled to capture any culture-related tags used to label photos shared online. Tags such as advertising, architecture, crafts, films, and publishing were hunted down, with photos taken in both New York and London analyzed. In total, they found around 1.5 million photos taken between 2010 and 2015.

Capitals of Culture

By geotagging each photo, researchers were able to assign them to one of 33 boroughs in London, or 70 community districts in New York. This then allowed them to both rank and compare changes in the cultural activity in each location over time.

This was then compared with published figures for urban development, which was the Index of Multiple Deprivation for London and the Social Vulnerability Index for New York. Add in data on house prices in each city and you had a reasonable proxy for the prosperity of each.

"We are able to show that economic capital alone does not explain urban development," the researchers say. "The combination of cultural capital and economic capital is more indicative of neighbourhood growth in terms of house prices and improvements of socio-economic conditions."

What's more, the team was also able to show how specific areas benefit from cultural activity by distinguishing the cultural boost from the economic.

Tourist Hotspots

It's not the first time that Flickr has been used by researchers to understand population-level behaviors. Several years ago, the Natural Capital Project conducted similar research to use Flickr photos to understand tourism patterns.

They mined the 1.4 million geo-tagged images on Flickr to get a picture of where people were going, and indeed where they were coming from. Then, they cross-profiled this against the visitor surveys from 836 recreational sites around the world. They found that the Flickr trends were a pretty reliable indicator of how many people both visit the tourist attraction each year and when they choose to do so.

"No one has been able to crack the problem of figuring out visitation rates and values for tourism and recreation without on-site studies until now," said Anne Guerry, lead scientist at the Natural Capital Project. Until now, researchers had to rely on local surveys and head counts to get this type of visitation information. Using social media to get ideas of where people are visiting and where they are coming from is faster, less expensive, and better for looking at changes over time and space.

Both studies provide an interesting insight into how social media data can be used to provide an accurate insight into how complex environments function.

Consuming AI in byte sized applications is the best way to transform digitally. #BuiltOnAI, EdgeVerve’s business application, provides you with everything you need to plug & play AI into your enterprise.  Learn more.

Topics:
flickr ,big data ,social media ,artificial intelligence ,ai

Published at DZone with permission of

Opinions expressed by DZone contributors are their own.

{{ parent.title || parent.header.title}}

{{ parent.tldr }}

{{ parent.urlSource.name }}