Regional Dialects on Twitter, and Other Things You Gotta Know

I was listening to All Things Considered yesterday while preparing dinner. A short, interesting story came on: You Have An Accent Even On Twitter. The NPR host, Robert Siegel, interviewed Jacob Eisenstein, a post-doc at Carnegie Mellon who has been examining regional variances in Twitter usage.

Some highlighted examples of Twitter dialecticisms:

In New York, people tend to do “suttin” (i.e. something, and usually having nothing to do with Sutton Place)

The use of “hella” to mean “very” as in “I’m hella tired” is more commonly iterated by people who’ve lived in Northern California.

(LOL is universally understood.)

I was sufficiently intrigued to track down Dr. Eisenstein’s paper, A Latent Variable Model for Geographical Lexical Variation, presented on January 8 at the annual meeting of the Linguistics Society of America in Pittsburgh. It’s a technical article befitting an MIT graduate, with un-trendy headings like “Cascading Topic Models,” “Inference” and heavy math. Still, I enjoyed the perusal.

Eisenstein and his colleagues started with a Gardenhose Twitter sample stream, which they say contained ~15% of public messages, from the first week of March, 2010. They whittled those down by selecting for tweets geo-tagged to the continental U.S. by authors who sent at least 20 messages during that period, and without URLs. Ultimately, they examined at some 380,000 Twitter messages (tweets) from 9,500 users.

The findings are really cool. (To be clear – that would be “coo” in Southern CA, or “koo” in Northern CA.)

Good to know that “af” signifies “as f-ck” (as in “very”), and is more commonly typed in Los Angeles than in some other parts. “Ima” for “I’m going to” is a New York kinda thing. “Gna” for “going to” is popular in Boston, but sounds familiar to this mother of a teenager in NYC.

From the Carnegie Mellon press release:

Studies of regional dialects traditionally have been based primarily on oral interviews, Eisenstein said, noting that written communication often is less reflective of regional influences because writing, even in blogs, tends to be formal and thus homogenized. But Twitter offers a new way of studying regional lexicon, he explained, because tweets are informal and conversational. Furthermore, people who tweet using mobile phones have the option of geotagging their messages with GPS coordinates.

…Automated analysis of Twitter message streams offers linguists an opportunity to watch regional dialects evolve in real time. “It will be interesting to see what happens. Will ‘suttin’ remain a word we see primarily in New York City, or will it spread?” Eisenstein asked.

I guess we’ll see how this progresses. I’m reminded of sometime around 8 years ago, when I tried cracking the IM code: “POS” meant “parent over shoulder.” That was easy. “Code 9” meant suttin similar, if I recall.


Related Posts:

Nice Nerds Needed

In last weekend’s edition of NPR’s Wait Wait…Don’t Tell Me!, host Peter Sagal asked a panelist about a serious problem facing the Pentagon: There’s a shortage of nerds, a.k.a. geeks.

Space Shuttle Atlantis (NASA image, Wikimedia Commons)

Happily, Houston Chronicle deputy editor and blogger Kyrie O’Connor came to the right answer.

On the quiz show, Sagal reported that Regina Dugan, head of DARPA (the Pentagon’s research arm and developer of the early Internet), recently testified before the House Armed Services Committee about her concern for our country’s most famous five-sided structure’s looming intellectual deficit.

“The decline in science education in this country means fewer nerds are being produced, a fact which has serious national security implications,” Sagal said in summary.

“Nerds molt into tech geeks. Tech geeks grow into scientists and scientists maintain the United States technical superiority,” he explained. No worries, though –

Sagal suggests the current nerd shortage will self-correct based on the predictable laws of high-school ecosystems. (To listen to his short description of this evolutionary process, check the track for Panel Round 2, after minute 4:48.)

Wired covered, earlier, the same story on DARPA’s looming technogeek shortage and Dugan’s forward-thinking statement on the matter:

…outlined her vision for the future of the Pentagon’s blue-sky research arm, with everything from plant-based vaccines to biomimetics making the short list. But none of it’s possible, she told the panel, without more investment in American universities and industry to cultivate the techies of the future…

So we lack sufficient math and science education to support the Pentagon’s needs for cutting-edge technology. And we all know that American businesses are losing out for the same reasons.

My concern is health, that some turned-on science and math-oriented kids should grow up and become physician-scientists or even plain-old, well-trained doctors who are good at interpreting graphs and applying detailed, technical information to patients with complex medical conditions. Last week I wrote that better education would improve health and medical care delivery in the U.S. This seems like an obvious point, but the more common discussion strikes on the need for math and science education to support hard technology in industry.

We’re facing a shortage of primary care physicians, oncologists and other doctor-types. Lots of clever and curious young people are turning away from medicine. The hours are too long, the pay’s too low, and the pressure is too great. If we want doctors who know what they’re doing, we should invest in their education and training, starting early on and pushing well past their graduation from med school.

Sure, we like physicians who are kind and honest people and can talk to them in ways they understand. This is crucial, but only to a point – we still depend on doctors to know their stuff.

I like doctors who are nice nerds. We need more of those, too.

Related Posts:

You’re Sick and I’m Not, Too Bad

“The insurance market as it works today basically slices and dices the population. It says, well you people with medical conditions, over here, and you people without them, over here…

– Jonathan Cohn, Editor of The New Republic, speaking on The Brian Lehrer Show, February 16, 2010*

There’s a popular, partly true, sometimes useful and very dangerous notion that we can control our health. Maybe even fend off cancer.

I like the idea that we can make smart choices, eat sensible amounts of whole foods and not the wrong foods, exercise, not smoke, maintain balance (whatever that means in 2010) and in doing so, be responsible for our health. Check, plus.

It’s an attractive concept, really, that we can determine our medical circumstances by informed decisions and a vital lifestyle. It appeals to the well – that we’re OK, on the other side, doing something right.

There is order in the world. God exists. etc.

Very appealing. There’s utility in this outlook, besides. To the extent that we can influence our well-being and lessen the likelihood of some diseases, of course we can!  and should adjust our lack-of-dieting, drinking, smoking, arms firing, boxing and whatever else damaging it is that we do to ourselves.

I’m all for people adjusting their behavior and knowing they’re accountable for the consequences. And I’m not keen on a victim’s mentality for those who are ill.

So far so good –

Last summer former Whole Foods CEO John Mackey offered an unsympathetic op-ed in The Wall Street Journal on the subject of health care reform. He provides the “correct” i.e. unedited version in the CEO’s blog:

“Many promoters of health care reform believe that people have an intrinsic ethical right to health care… While all of us can empathize with those who are sick, how can we say that all people have any more of an intrinsic right to health care than they have an intrinsic right to food, clothing, owning their own homes, a car or a personal computer? …

“Rather than increase governmental spending and control, what we need to do is address the root causes of disease and poor health.  This begins with the realization that every American adult is responsible for their own health.  Unfortunately many of our health care problems are self-inflicted…

Now, here’s the rub. While all of us can empathize, not everyone does. And few citizens go to medical school. Some, uneducated or misinformed, might sincerely believe that illnesses are deserved.

So let’s set some facts straight on real illness and would-be uninsurable people like me:

Most people who are sick – with leukemia, diabetes, osteogenesis imperfecta, heart disease, multiple sclerosis, scoliosis, glycogen storage disease Type II, depression, Lou Gehrig’s disease, sickle cell anemia, rheumatoid arthritis or what have you – are not ill by choice. They didn’t make bad decisions or do anything worse, on average, than people who are healthy.

Rather, they became ill. Just like that.

The idea of an insurance pool is that when everyone in the community participates, whoever ends up with large medical expenses is covered, explained Jonathan Cohn. When contributions come in from all, including those who are healthy, funds are sufficient to provide for the sick among us.

As things stand, the insurance industry divides us into likely profitable and unprofitable segments. “So you know if you’re one of the people born with diabetes, you have cancer, you had an injury that requires lengthy rehabilitation, tough luck, you’re going to end up in that pool of unhealthy people,” Cohn said.

Insurance is no cure-all, to be sure. It won’t take away my cousin’s cancer or fix Bill Clinton’s heart. That would require research and better medicines.

Depriving insurance, or care, to those who need it most is inconceivable to a society as ours was intended. It’s uncivil.

*as heard on The Brian Lehrer Show 2/16/10: Rates on the Rise

Related Posts:

newsletter software
Get Adobe Flash player