Artificial neural networks for predicting social comparison effects among female Instagram users

PLoS One. 2020 Feb 25;15(2):e0229354. doi: 10.1371/journal.pone.0229354. eCollection 2020.

Abstract

Systematic exposure to social media causes social comparisons, especially among women who compare their image to others; they are particularly vulnerable to mood decrease, self-objectification, body concerns, and lower perception of themselves. This study first investigates the possible links between life satisfaction, self-esteem, anxiety, depression, and the intensity of Instagram use with a social comparison model. In the study, 974 women age 18-49 who were Instagram users voluntarily participated, completing a questionnaire. The results suggest associations between the analyzed psychological data and social comparison types. Then, artificial neural networks models were implemented to predict the type of such comparison (positive, negative, equal) based on the aforementioned psychological traits. The models were able to properly predict between 71% and 82% of cases. As human behavior analysis has been a subject of study in various fields of science, this paper contributes towards understanding the role of artificial intelligence methods for analyzing behavioral data in psychology.

MeSH terms

  • Adolescent
  • Adult
  • Anxiety / diagnosis
  • Anxiety / epidemiology
  • Anxiety / psychology*
  • Artificial Intelligence*
  • Depression / diagnosis
  • Depression / epidemiology
  • Depression / psychology*
  • Female
  • Humans
  • Middle Aged
  • Poland / epidemiology
  • Self Concept*
  • Social Behavior*
  • Social Media / statistics & numerical data*
  • Social Networking*
  • Surveys and Questionnaires
  • Young Adult

Grants and funding

The author(s) received no specific funding for this work.