Is That a Y'all In Your Tweet? Study Shows Regional Accents on Twitter

If you write, "Coo" in a tweet, you're probably from Southern California. If you opt for "koo," you're probably from up north. "Uu" means you likely hail from New York, while "Yu" means you're rural. Twitter stereotypes? Nope, just the facts, according to new research showing regional "accents" are not just of the spoken kind.

If you write, “Coo” in a tweet, you’re probably from Southern California. If you opt for “koo,” you’re probably from up north. “Uu” means you likely hail from New York, while “Yu” means you’re rural. Twitter stereotypes? Nope, just the facts, according to new research showing regional “accents” are not just of the spoken kind.

Researchers at Carnegie Mellon University examined 380,000 messages from Twitter during one week last March and found they could pinpoint a user’s location to within 300 miles by analyzing the vocabulary in the tweets.

For example:

  • New York City residents often use “suttin” for “something,” “youu” for “you” and “II” for “I.”
  • Northern Californians use “koo” for “cool,” while Southern Californians like “coo.”
  • To describe how tired they are, New Yorkers like “deadass” as an adjective, Northern Californians use “hella,” and LA residents use the abbreviation “af” after the word (as in, “I’m tired as f—“)
  • “Ya’ll” shows up a lot in the South, while its Pennsylvania equivalent, “yinz” is big in the Pittsburgh area.

Lead researcher Jacob Eisenstein and his colleagues in Carnegie Mellon’s Machine Learning Department analyzed the geotags attached to Twitter messages sent from mobile phones for the study, examining 4.5 million words in all.

“I think that it shows is that people really have a need to communicate their identity – their cultural identity and their geographic identity in social media,” said Eisenstein.

Researchers turned to Twitter in particular as the preferred social media site to study because its users tend to tweet in more casual, abbreviated vocabulary.

“Written communication often is less reflective of regional influences because writing, even in blogs, tends to be formal, and thus homogenized,” the study team said in a statement to Reuters.

Some of the differences in tweets can be explained by the need to write concisely to fit the site’s 140-character limit. But others, not so much, such as New Yorkers stretching “you” to “youu,” instead of the typical shortened “u,” or stretching “I” to “II.”

Researchers at Carnegie Mellon University plan to present the study this month at the Linguistic Society of America meeting in Pittsburgh.