Using Artificial Intelligence (AI) and data from various social media sites, researchers tracked people's physical activities, from bowling to crossfit, in a bid to inform future efforts to tackle health disparities.
Published in the journal BMJ Open Sport & Exercise Medicine, the researchers used machine learning to find and comb through exercise-related tweets from across the US, unpacking regional and gender differences in exercise types and intensity levels.
By analysing the language of the tweets, this method was also able to show how different populations feel about different kinds of exercise.
"In most cases, lower-income communities tend to lack access to resources that encourage a healthy lifestyle," said study author Elaine Nsoesie, Assistant Professor at the Boston University in the US.
"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.
For the study, the researchers used a set of AI models to find and analyse 1,382,284 relevant tweets by 481,146 Twitter users in 2,900 US counties.
The researchers compared tweets by men and women and from four different regions of the country: the Northeast, the South, the Midwest and the West.
According to the findings, the top exercise terms were "walk", "dance", "golf", "workout", "run", "pool", "hike", "yoga", "swim" and "bowl". Walking was the most popular activity overall, but other activities varied by gender and region.
Women in the West 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, said the study.