Computer science researchers have figured out a way to use tweets for better urban planning.
When you send a tweet, often they are tagged with what’s called a geolocation, which identifies the location from which you’re tweeting. Researchers (and siblings) Enrique and Vanessa Frías-Martínez, who work at Telefonica Research and the University of Maryland, deduced a way to gather that data and identify where the city’s nightlife thrives the most.
A common problem among urban planning is forgetting to account for how land is used during the nighttime versus during the day. However, nightlife is important to take into account when it comes to factors like foot traffic and noise control.
Enrique and Vanessa realized that in big cities with millions of people, having location tags as well as time stamps provides an accurate picture of where people spend their time at certain points in the day. They were particularly interested in honing in on the evening data.
Getting this type of information in detail often involves the use of questionnaires, a process that can be both time-consuming and expensive for urban planners, but aggregating tweets is simple and quick.
The duo has already tested their method on Manhattan, Madrid, and London, and their study is published in the journal Engineering Applications of Artificial Intelligence. The were able to differentiate residential, business, daytime leisure and nightlife areas from aggregated tweets alone. They found that night activity in Madrid was more concentrated on weekends compared to Manhattan where more activity was during weeknights. London has especially high activity in daytime areas.
More Must-Reads from TIME
- Introducing the 2024 TIME100 Next
- The Reinvention of J.D. Vance
- How to Survive Election Season Without Losing Your Mind
- Welcome to the Golden Age of Scams
- Did the Pandemic Break Our Brains?
- The Many Lives of Jack Antonoff
- 33 True Crime Documentaries That Shaped the Genre
- Why Gut Health Issues Are More Common in Women
Contact us at letters@time.com