Skip to main content
  1. Home
  2. Emerging Tech
  3. Computing
  4. Social Media
  5. News

You are what you tweet: Twitter reveals how America eats and exercises

Add as a preferred source on Google

Twitter, it turns out, isn’t just about wacky hashtags and slandering celebrities anonymously.

A new tool developed by researchers at the University of Vermont’s Computational Story Lab — along with those at the University of California, Berkeley, Massachusetts Institute of Technology, and several others universities — is using the social network to track how America is eating and exercising.

Recommended Videos

Called the Lexicocalorimeter, it searches for thousands of activities and foods, and assigns them approximate calorie number, with the broad idea being that tagged phrases are split into “caloric input” and “caloric output” categories. These aren’t just your everyday “running” and “pushups” type exercises, either: the researchers have included the likes of “pole dancing” and “alligator hunting” among the things it’s looking for. Case in point: One of America’s favorite “activities” is watching television.

The goal is to see what kind of caloric balance exists around the United States, with positive examples being set by places like Colorado (“running” as activity, and “noodles” as food), while Mississippi sadly ranks at the other end of the spectrum (“eating” and “cake.”)

True, it’s not super accurate, but it’s the kind of insight that is only possible to start exploring in an age of social media.

“We’ve had an amazing explosion of information, with people expressing themselves online through social media,” Peter Dodds, a scientist at the University of Vermont, told Digital Trends. “This research is an attempt to use that to look at population health patterns on a country, state, and city basis.” He describes the results as a “dashboard of society.”

Eventually, it will be possible to monitor everything in real time but for now, you will have to settle for looking at the results of 50 million geo-tagged tweets from 2011 and 2012.

“On an individual level, I think this can be interesting because it allows you to compare yourself or your state to people living elsewhere in the country, for example,” Dodds continued. “You could also do the same over a period of time, which allows you to reflect on whether things are getting better or worse. From a city planner or policy-making perspective, it could also be incredibly important. If you can see these numbers in front of you, it would be possible to look at what happened in another city when they introduced a particular program to see whether it was effective.”

In all, it’s another amazing demonstration of the way that even seemingly throwaway social media comments are helping document the age we live in.

“Just imagine if we had these tools going back 100 years,” Dodds said. “You would see remarkable transformations taking place in the kinds of food and exercise that people talked about. Going forward, we hope that this lasts for a very long time.”

You can check out the Lexicocalorimeter here.

Luke Dormehl
I'm a UK-based tech writer covering Cool Tech at Digital Trends. I've also written for Fast Company, Wired, the Guardian…
Researchers hid a prompt injection inside a PNG, and AI fell for it
Hacker

AI coding assistants like Claude are becoming every developer's favorite coworker. They can review code, explain confusing functions, and even write entire features with a single prompt. But new research suggests that this growing trust could also become their biggest weakness.

A team of security researchers (professor Sudipta Chattopadhyay and researcher Murali Ediga) has demonstrated an unusual attack that doesn't target the AI model directly. Instead, it targets what the AI doesn't pay enough attention to during code reviews. Rather than hiding malicious instructions in lines of code, the researchers tucked them inside an image file. Since many AI review tools treat images as decorative assets rather than as something worth inspecting, the pull request can appear perfectly harmless and sail through the review.

Read more
AI has already fallen into the wrong hands and they’re using it to make bombs
Logo, Text

Artificial intelligence has quickly become the go-to tool for everything from writing emails and summarizing meetings to helping students study or developers debug code. But the same technology that saves people time can also be misused, and a new report suggests that terrorist organizations are finding ways to do exactly that.

According to a research paper shared with The New York Times ahead of its publication, researchers found evidence that members of Boko Haram have been using popular AI chatbots to support both day-to-day activities and combat-related tasks. Interviews with 27 former members conducted in Nigeria over the past two years suggest that tools such as ChatGPT, Gemini, Claude, Grok, Meta AI, and DeepSeek were used to gather technical information, troubleshoot weapons, and even assist with planning attacks.

Read more
Claude Code can now browse the web without opening Chrome
The desktop app now includes an in-app browser that can read websites, click links, and interact with web apps.
Claude Code Featured

Developers spend a surprising amount of time bouncing between their code editor, browser tabs, API documentation, GitHub issues, and design files. Anthropic thinks Claude Code should simply do all of that without constantly asking users to switch windows. The company has announced a new in-app browser for Claude Code on desktop, allowing its AI coding assistant to open websites, read documentation, inspect designs, and interact with web pages directly from within the application.

A browser built into Claude Code

Read more