Examining the utility of nonlinear machine learning approaches versus linear regression for predicting body image outcomes: The U.S. Body Project I. (June 2022)

• Record Type: Journal Article
• Authors: Liang, Dehua; Frederick, David A.; Lledo, Elia E.; Rosenfield, Natalia; Berardi, Vincent; Linstead, Erik; Maoz, Uri
• Is Part Of: Body image. Volume 41(2022)
• Page Start: 32
• Page End: 45
• Publication Date: 2022-06
• Subjects: Body image -- Tripartite model -- Random forest -- Deep neural networks -- Machine learning; Body image -- Periodicals; Body image -- Research -- Periodicals; Body Image -- Periodicals; 306.4613
• DOI: 10.1016/j.bodyim.2022.01.013
• Languages: English
• ISSNs: 1740-1445

Abstract

Highlights: Most body image studies examine only linear associations among variables. Machine learning algorithms examine complex linear and nonlinear associations. We compared Random Forest, Neural Network, and Linear Regression analyses. Random Forest was sometimes slightly superior for maximizing adj. R 2 . This provides one example for how to apply machine learning in body image field. Abstract: Most body image studies assess only linear relations between predictors and outcome variables, relying on techniques such as multiple Linear Regression. These predictor variables are often validated multi-item measures that aggregate individual items into a single scale. The advent of machine learning has made it possible to apply Nonlinear Regression algorithms—such as Random Forest and Deep Neural Networks—to identify potentially complex linear and nonlinear connections between a multitude of predictors (e.g., all individual items from a scale) and outcome (output) variables. Using a national dataset, we tested the extent to which these techniques allowed us to explain a greater share of the variance in body-image outcomes ( adjusted R 2 ) than possible with Linear Regression. We examined how well the connections between body dissatisfaction and dieting behavior could be predicted from demographic factors and measures derived from objectification theory and the tripartite-influence model. In this particular case, although Random Forest analyses sometimes provided greater predictive power than Linear Regression models, the advantages were small. More generally, however, this paper demonstrates how body image researchers might harness the power of machine learning techniques to identify previously undiscovered relations among body image variables.