The 140-character tweets posted on Twitter can reveal a great deal about the health of Americans. A new study used the microblogging site to gain insights on the health of people in the United States and, in the process, found the most popularly tweeted foods.
In a new study published in the Journal of Medical Internet Research - Public Health, researchers from the University of Utah used federal grant money to see if social media can paint a picture of the nation's health.
The researchers looked at 80 million geotagged tweets from more than 603,000 Twitter users across the United States and found the most tweeted-about foods, the most popular of which is coffee, which was mentioned in 250,000 tweets. The caffeinated drink is followed by beer, which was mentioned in more than 200,000 tweets.
Below is the list of the top 10 most popular foods on Twitter:
1. coffee
2. beer
3. pizza
4. Starbucks
5. IPA (beer)
6. wine
7. chicken
8. barbecue
9. ice cream
10. tacos
Although only about 5 percent of the analyzed tweets mentioned food, the results hinted the health of Americans in neighborhoods across the country based on what they share on social media. By comparing geolocated tweets to health surveys and census data, the researchers were able to learn about the health of the populace in certain parts of the U.S.
Of the collected tweets that mentioned food, 16 percent were about healthy foods, while 9 percent were about fast food.
The researchers likewise found that tweets sent from poorer neighborhoods do not tend to mention healthy foods, while areas with more tweets about healthy food were found to have lower rates of death and chronic diseases.
Other than food, the researchers were also able to gather data on the physical and emotional health of Americans based on what they post on Twitter albeit the algorithm researchers used were not perfect.
"Access to neighborhood data," the researchers wrote, "can be leveraged to better understand neighborhood effects and address social determinants of health. We found that neighborhoods with social and economic disadvantage, high urbanicity, and more fast food restaurants may exhibit lower happiness and fewer healthy behaviors."
Study author Quynh Nguyen, from the University of Utah College of Health, believes that with more refinement, the messages that people post on social media can offer untapped insights into public health.
"So far, we are finding that they do predict area-level health outcomes at various levels: zip code, census tract, county and state," Nguyen said.
