V.G. Vinod Vydiswaran, assistant professor in the Department of Learning Health Sciences at the University of Michigan was the lead author on a new paper in the Journal of the American Medical Informatics Association. He said, “We wondered whether Twitter-based analysis could help us understand communities better.”
Researchers used community-based surveys to gather demographic and health-related behavior information. The data might help explain health status and disparities between groups. For Vydiswaran and fellow researchers, the focus was on food. They also wanted to know whether there were differences between how groups of residents of a given region discussed food.
The analysis of the study began by scoring different food-related keywords, including types of foods, modes of preparation, and popular restaurants based on their healthiness. Foods were defined on a scale of very unhealthy to very healthy, based on dietary attributes such as trans-fat or added sugar.
We found differences in the kinds of foods people tweet about in neighborhoods. More affluent neighborhoods included the top keywords in their tweets such as Starbucks, coffee, and vegan. Whereas terms like pizza, tacos, and bacon were common in less affluent neighborhoods, says Vydiswaran.
Twitter’s API (Application programming interface) was an interface which allows software access to Twitter’s data. By using API, The researchers gathered geo-tagged tweets from more than 1,200 census tracts around the local area. With a data set of more than 800,000 food-related tweets from over 62,000 unique tweeters, the group conducted sentiment analysis. This helped in determining whether the content of each tweet trended negative or positive. They removed tweets belonging to celebrity influencers or marketing tweets that might artificially affect the online conversation.
“We found differences in the kinds of foods people tweet about in neighborhoods,” said Vydiswaran. More affluent neighborhoods included the top keywords in their tweets such as Starbucks, coffee, and vegan. Whereas terms like pizza, tacos, and bacon were common in less affluent neighborhoods. Net healthiness scores were best explained by affluence, fast food density, and the number of tweets, with less affluent areas discussing unhealthier foods.
Next, they looked for correlations between Twitter content and neighborhood demographics. It was found that neighborhoods with a higher percentage of African-American residents had more positive sentiment about food, both healthy and unhealthy. Said Vydiswaran, “We hypothesize that one possible reason behind this is that the enjoyment of food is a part of the culture.”
They also found that more affluent areas had less positive sentiment about food than other topics. Though less affluent areas had more positive food sentiment.
Finally, they looked at the correlation in food-related tweeting and mortality rates from the top five obesity-related causes of death: diabetes, heart failure, kidney failure, stroke and heart disease.
“In the multivariate regression analysis, accounting for other neighborhood measures such as affluence and percentage African American, our Twitter-based food healthiness measure was still significantly correlated with one obesity-linked condition, heart failure,” said Vydiswaran.
The authors noted that tweets were an imperfect measure of behavior (for example, they don’t necessarily account for the amount of food consumed) and that Twitter users might not have represented the total population of an area. However, more traditional surveys also suffered from bias and were often much harder to conduct than social media analysis.
“We are proposing using social media as an additional source of input for policymakers to understand neighbors,” he said. “Social determinants of health, such as neighborhood walkability, mentions of food deserts, safety concerns — these kinds of references show up in tweets and could act as additional input for researchers wanting to understand how they affect health more generally.”
-article published in Michigan Medicine Lab Blog