News Technology

Coffee is the Most Popular Food on Twitter, Finds New Study

A new study carried out by researchers at the University of Utah has found that coffee is the most tweeted-about consumable in the United States.

The researchers—who received $721,825 from the National Institutes of Health (NIH) to carry out this study—analyzed about 80 million tweets sent by 603,363 unique users between April 2015 and March 2016. The aim of the study was to gain insight into the health of people in the U.S. and to develop “HashtagHealth,” a database of publicly available social media posts about food.

“Increasingly we’re seeing more and more studies looking at health beyond just disease, incorporating indicators of wellbeing,” says Quynh Nguyen, an assistant professor at the University of Utah College of Health and the lead author of the study.

The team studied the tweets about physical activity, food, and happiness, and compared their results with health surveys and census data. They found that only 5% of the tweets collected from 2015-2016 mentioned about food. In such tweets, coffee was the most-mentioned edible followed by beer, pizza, wine, chicken, BBQ, ice cream and tacos.

Starbucks was found to be the most popular fast-food restaurant, followed by Chipotle, Taco Bell and Buffalo Wild Wings. Starbucks was mentioned in about 50% of tweets which talked about fast-food restaurants.

It was interested to see that tweets coming from poorer neighborhoods mentioned very little about healthy foods. However, areas that tweeted more about healthy foods were those having lower rates of chronic disease and fewer counts of deaths.

Similarly, tweets about physical activity (only 2% of all tweets) mostly came from areas with lower rates of obesity and fewer deaths. The physical activity that were mentioned most in such tweets were walking, dancing, running, workouts, golf, swimming, hiking, yoga and bowling.

“What was kind of nice, from a health and emotion perspective, was that tweets that mentioned food were actually happier than tweets that did not mention food, and tweets that mention healthy foods were the happiest,” Nguyen says.

“Healthy food and physical activity were the happiest kind of tweets.”

Nguyen suggests that in future, messages from social media could become a good medium of getting insights into our health.

“So far, we are finding that they do predict area-level health outcomes at various levels: zip code, census tract, county and state,” she says. “Our next set of analyses examine whether these social environment variables predict individual-level health outcomes.”

The HashtagHealth project is part of NIH’s Big Data To Knowledge program, and its ultimate goal “harnessing the largely untapped potential of social media data to capture social and cultural processes with potential impact on health.”

The detailed findings of the study have been published in the Journal of Medical Internet Research Public Health and Surveillance.