Boston University School of Public Health (BUSPH) has combined social media posts and machine learning to chart entire populations' exercise habits.
BUSPH researchers combed through exercise-related tweets from across the US and analysed the language of the tweets to uncover how different populations feel about different kinds of exercise.
The researchers used a set of artificial intelligence models to find and analyse more than 1.38m relevant tweets by 481,146 individual Twitter users in 2,900 US counties.
By doing so, researchers were able to unpack regional and gender differences in exercise types and intensity levels.
According to Dr. Elaine Nsoesie, assistant professor of global health at BUSPH. the research unearthed insight that could be used to help make populations more active.
"By understanding differences in how people are exercising across different communities, we can design interventions that target the specific needs of those communities," Nsoesie said.
"The study showed that, in most cases, lower-income communities tend to lack access to resources that encourage a healthy lifestyle."
Dr. Nina Cesare, study senior author and postdoctoral associate in global health at BUSPH, added: "In the future, social media and other digital data could help create interventions and policies informed not just by the habits of these communities, but also by what they think of different physical activities.
"We believe this work provides a step in the right direction."
The top exercise terms were walking, dance, golf, workout, run, pool, hike, yoga and swim.
Walking was the most popular activity overall, but other activities varied by gender and region.
Findings included that women in the West of US did more intensive exercise than in any other region, while the Midwest had the most intensive exercise among men. Men did slightly more intensive exercise than women overall, and South had the biggest gender gap in exercise intensity.
The research was published in BMJ Open Sport & Exercise Medicine. To read the full article,
click here.
