Researchers Use Twitter To Determine Heart Attack Risk

I love Twitter. Besides all the conversations and the relationships I’ve built being on the platform, I love it because it’s opening itself up to new and more interesting developments that not just impact our social status but our future in so many capacities.

Sure, at some points it can be overrun with advertisements, Twitter chats, advertisements through Twitter chats, but in the end, I like it more than any other social network. Moving on, I’m sure you’ve all seen this already as it was picked up by the New York Times and now Fast Company: Your Tweets Can Tell if You’re Going To Have a Heart Attack.

LanguageWhen I saw that, I was appalled. Really? What is the reasoning behind this, I wondered. And then I thought, am I going to have a heart attack?

So I took to Penn News and read about the study that was done. Just so you know, this is a cross between psychology, computer and information science and engineering. They took the old-fashioned idea of surveys meant to measure the emotions and feelings of people and applied the theory to Twitter, drawing from the language chosen and emotional states of individuals.

Since coronary heart disease is the leading cause of death worldwide, the five researchers (among them one woman) decided to see if they could show connections between emotional states and physical outcomes using Twitter.

Margaret Kern, an assistant professor and the University of Melbourne, Australia, was the one woman researcher:

“Psychological states have long been thought to have an effect on coronary heart disease,” said Kern. “For example, hostility and depression have been linked with heart disease at the individual level through biological effects. But negative emotions can also trigger behavioral and social responses; you are also more likely to drink, eat poorly and be isolated from other people which can indirectly lead to heart disease.”

So off they went, pulling a set of public tweets from 2009 to 2010, establishing “emotional dictionaries” and word clusters that showed behaviors and attitudes. The tweets sampled also came from those who allowed for geo-tagging of their tweets, coming from “1,300 counties which hold 88 percent of the country’s population.”

What they found was that if people are more prone to writing expletives and are angry in their tweets, they are CDC Twitter Mapencircled by a community full of anger, which may make them prone to dying from heart disease. Whereas using positive words protected individuals from heart disease. They seemed to find a high-level, long-term communal characteristic.

What if my life actually sucks but I like to play the fact that I’m careless and fancy free and happy on social? Well, they found that it varied from location to location– down to the zip code.

Gregory Park is a postdoctoral fellow in the department of Psychology:

“Twitter seems to capture a lot of the same information that you get from health and demographic indicators,” Park said, “but it also adds something extra. So predictions from Twitter can actually be more accurate than using a set of traditional variables.”

When lined up with the CDC’s map of heart disease happenings, what this team of researchers found was that it was surprisingly accurate in the end. How cool is that? The innovation of thought process is incredible. Does this mean that the rate of diabetes can also be determined since it is closely tied to heart-disease? I wonder.

I wonder what people would be able to tell from Facebook statuses?

Advertisements

Leave a comment

Filed under Health, Research

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s