Skip to main content

A new algorithm can tell when you’re tweeting while drunk, and may help save lives

Twitter Followers Landis
The only thing worse than drunk texting? Drunk tweeting, duh. Because when you’re drunk, the last thing you want is an audience, especially when that audience is the Twitter-verse. But if you’ve drunk tweeted in the past, you can regain a bit of dignity by knowing that you’ve contributed to some great research that now allows scientists to detect just how inebriated you are when using social media — or stated more simply, whether or not your latest Twitter contribution was made in a drunken stupor.

In truly monumental research, Nabil Hossain at the University of Rochester took Twitter and machine learning, and smashed them together to determine drinking habits across specific geographic locations. Hossain and his team rounded up thousands of geotagged posts that appeared on Twitter between July of 2013 and July of 2014 across the state of New York, and then parsed them down to only examine tweets that contained alcohol-related keywords (think “beer keg,” “drunk,” and the like).

This ultimately gave them a database of about 11,000 tweets to work with, which the researchers passed through Amazon’s Mechanical Turk crowdsourcing service. Every single one of those thousands of tweets were examined by three human “Turkers,” who answered three questions about the posts:

  1. Does the tweet make any reference to drinking alcoholic beverages?
  2. If so, is the tweet about the tweeter him or herself drinking alcoholic beverages?
  3. If so, is it likely that the tweet was sent at the time and place the tweeter was drinking alcoholic beverages?

The answers derived from these questions gave the team a sense of whether or not the tweets came from folks who were drinking or drunk. Then, going even further with their research, Hossain and his team looked into where the tweeters were when they were imbibing (or at the very least, drunk tweeting). By the end of their efforts, they’d managed to create an algorithm that theoretically can pinpoint whether a user was at home when drunk tweeting with up to 80-percent accuracy.

By combining these two determinations, Hossain says that his research group can now determine where New Yorkers prefer to drink, and by extension, identify their favorite watering holes. “Our results demonstrate that tweets can provide powerful and fine-grained cues of activities going on in cities,” Hossain’s team notes, and tracking this sort of activity could help keep drinkers out of harm’s way. 

So don’t be embarrassed by your drunk tweets (not for this reason at least). After all, they could save your life.

Editors' Recommendations

Vulnerability steals data from Intel and AMD CPUs — and you’re probably affected
A technician placing a CPU into a motherboard socket for a PC.

Researchers just outlined a new vulnerability that affects processor chips -- and it's called Hertzbleed. If used to conduct a cybersecurity attack, this vulnerability can help the attacker steal secret cryptographic keys.

The scale of the vulnerability is somewhat staggering: According to the researchers, most Intel and AMD CPUs might be impacted. Should we be worried about Hertzbleed?

Read more
Sleep apps are booming but experts warn they are not perfect
A woman lays in bed using her cellphone.

A growing selection of mobile apps purports to help you fall asleep and measure the quality of your slumber as a record number of Americans deal with insomnia.

Subscription-based apps like Loona offer stories read in a soothing voice and sounds meant to be calming and block out noises. Other apps like SleepScore claim to measure the amount of sleep you are getting and let you know if it’s enough. But some medical professionals expressed doubts about whether apps like these help.

Read more
6 Google I/O 2022 streams to watch even if you’re not a developer
Google I/O

Google I/O takes May 11 and May 12 this year, and the annual event is where Google entertains its developer community, bringing it together both in person and virtually to learn about what’s new in Android, WearOS, and other Google tools and technologies. But just because it’s primarily developer-focused doesn’t mean there isn’t anything for non-developers to enjoy.

To help those with an interest in Google and Android navigate Google I/O’s many streamed keynotes, panels, and product demonstrations, here are our recommendations of the sessions to watch even if you’re not a developer. Google I/O will be livestreamed in its entirety, and all the streams should be available to watch for free, although you may need a Google Developer account to do so.
Google I/O keynote
10 a.m. PT on May 11

Read more