Artificial intelligence (AI) and social media can provide more accurate assessments of depression and anxiety in American communities than traditional surveys, according to a study led by researchers from Stony Brook University, Stanford University, and the University of Pennsylvania. The study analyzed nearly one billion tweets from over two million users in 1,418 US counties and found that AI-generated measurements were more reliable at tracking changes in mental health rates on a weekly level and for smaller regions. The researchers recommended incorporating language-based assessments alongside traditional survey data to obtain a more accurate and timely understanding of community mental health.