Twitter Knows Why You're Eating So Much: Researchers Use Social Media To Track Dietary Choices
Mostly everyone knows sharing your last meal on Twitter breaks etiquette. But for the health-conscious user, keeping a digital log of daily eating habits has been found to be an effective method for visualizing data and receiving digestible feedback for further use.
Researchers at the University of Arizona recruited 50 adults, aged 18-30, to participate in a recent study that utilized Twitter for just such a purpose. Users tracked their daily meals on specially made Twitter accounts and drew from 24 pre-made hashtags that would let researchers later analyze eating habits. In the end, the team collected data from 773 tweets including 2,862 hashtags (1,756 foods and 1,106 reasons for eating), eventually determining convenience and taste as the two most frequent causes of eating.
"This helps us understand what is driving eating behavior, and that's important from a healthy eating program standpoint," said lead author Dr. Melanie Hingle. "If I am going to develop a program to promote healthy eating to people, I want to know what motivates them to engage in their current eating behavior so I can tailor that program appropriately."
Participants tweeted everything they ate or drank for three consecutive days, using hashtags such as “#grains,” “#dairy,” and “#protein.” The research has promising implications for letting users keep up-to-date on their own habits, Hingle noted, as eating can easily become an unconscious process riddled with mindless snacking.
"It's good to raise awareness about your habits since a lot of eating behavior is unconscious or really habitual," she told Yahoo! Shine. "You tend to get in your groove and not get out of it, so this kind of shakes that up and makes you think about what's influencing you. It can help you develop new habits or just become aware of the ones that are not doing you any good."
In either case, greater access to information seems to be the hallmark of Hingle’s study. While Twitter has undoubted capabilities to reach people socially, exploiting it for personal use hasn’t amassed nearly the same popularity. It’s Hingle’s hope that people will use the platform for better understanding their choices.
"We were able to visualize relationships between eating behaviors and reasons for those behaviors in a novel way we haven't really done before," she said. "That allowed us to really see that there are, in fact, relationships, and those relationships do seem to align with the ones in the literature, which shows that convenience and cost are among the main motivators."
Such relationships have also branched out to matters of safety. Researchers from the University of Rochester recently used Twitter’s GPS function to locate 28,000 restaurant visitors among 3.8 million tweets. They were using the data to track potential cases of food poisoning, noting when a user went out to eat and where, before checking back a few days later for tweets with keywords suggesting illness. The team found 480 possible cases of food poisoning, as Henry Kautz wrote in the New York Times.
“The Twitter reports are not an exact indicator — any individual case could well be caused by factors unrelated to the restaurant meal. But in aggregate the numbers are revealing,” Kautz wrote, adding the team “compared the results with the current database of restaurant inspections conducted by New York City’s Department of Health and Mental Hygiene.”
“We found significant correlation between restaurants’ violation scores and the Twitter-based scores,” he added.
And while Kautz conceded the use of social media analysis likely won’t enter the public policy realm anytime soon, what the platform does have going for it is its timeliness. Quick feedback lets users keep a finger on the pulse in real-time, at all times.
“While city health inspections capture a wide variety of data that is difficult to obtain from online social media (like the presence of rodents in a restaurant’s storage room),” noted Kautz, “the Twitter signal measures a perhaps more useful quantity: a probability estimate of your becoming ill if you visit a particular restaurant.”
Source: Hingle M, Yoon D, Fowler J. Collection and Visualization of Dietary Behavior and Reasons for Eating Using Twitter. Journal of Medical Internet Research. 2013.