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

Dehua Liang; David A Frederick; Elia E Lledo; Natalia Rosenfield; Vincent Berardi; Erik Linstead; Uri Maoz

doi:10.1016/j.bodyim.2022.01.013

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

Body Image. 2022 Jun:41:32-45. doi: 10.1016/j.bodyim.2022.01.013. Epub 2022 Feb 25.

Authors

Dehua Liang¹, David A Frederick², Elia E Lledo³, Natalia Rosenfield³, Vincent Berardi⁴, Erik Linstead³, Uri Maoz⁵

Affiliations

¹ Fowler School of Engineering, Chapman University, Orange, CA, USA; Schmid College of Sciences and Technology, Chapman University, Orange, CA, USA.
² Crean College of Health and Behavioral Sciences, Chapman University, Orange, CA, USA. Electronic address: dfrederi@chapman.edu.
³ Fowler School of Engineering, Chapman University, Orange, CA, USA.
⁴ Fowler School of Engineering, Chapman University, Orange, CA, USA; Crean College of Health and Behavioral Sciences, Chapman University, Orange, CA, USA.
⁵ Fowler School of Engineering, Chapman University, Orange, CA, USA; Schmid College of Sciences and Technology, Chapman University, Orange, CA, USA; Crean College of Health and Behavioral Sciences, Chapman University, Orange, CA, USA; Institute for Interdisciplinary Brain and Behavioral Sciences, Chapman University, Orange, CA, USA.

PMID: 35228102
DOI: 10.1016/j.bodyim.2022.01.013

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 R²) 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.

Keywords: Body image; Deep neural networks; Machine learning; Random forest; Tripartite model.

MeSH terms

Body Image* / psychology
Humans
Linear Models
Machine Learning*