Boston University School of Public Health researchers used machine learning (artificial intelligence) to analyze exercise-related tweets. The goal was to understand how gender and regional differences influenced some exercise behaviors across the U.S.

Walking was the most popular activity. Western women and Midwestern men did more intensive exercise than those in any other region. The South had the biggest gender gap in exercise intensity.

The study is available in BMJ Open Sport & Exercise Medicine (2019; 5 [e0005667]).