首页|University of Texas Austin Reports Findings in Machine Learning (Complex Emotion Dynamics Contribute to the Prediction of Depression: A Machine Learning and Tim e Series Feature Extraction Approach)
University of Texas Austin Reports Findings in Machine Learning (Complex Emotion Dynamics Contribute to the Prediction of Depression: A Machine Learning and Tim e Series Feature Extraction Approach)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in Austin, Texas, by NewsRx journalists, research stated, "Emotion dynamics have demonstrated mix ed ability to predict depressive symptoms and outperform traditional metrics lik e the mean and standard deviation of emotion reports. Here, we expand the types of emotion dynamic features used in prior work and apply a machine learning algo rithm to predict depression symptoms." The news reporters obtained a quote from the research from the University of Tex as Austin, "We obtained seven ecological momentary assessment (EMA) studies from previous work on depression and emotion dynamics ( = 890). These studies measur ed self-reported sadness, positive affect, and negative affect 5 to 10 times per day for 7 to 21 days (schedule varied across studies). These data were fed thro ugh a feature extraction routine to generate hundreds of emotion dynamic feature s. A gradient boosting machine (GBM) using all available emotion dynamics featur es was the best of all models assessed. This model's out-of-sample prediction ( ) for depression severity ranged from .20 to .44 depending on EMA interpolation method and samples included in the analysis. It also explained significantly mor e variance than a benchmark model of individuals' mean emotion ratings over the assessment period, = .089."
AustinTexasUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
