ABSTRACT. This paper draws on a substantial body of theoretical and empirical research on visual sentiment and affective computing algorithms, deep learning-based multimodal emotion recognition and automated digital beauty technologies, and 3D machine learning-based facial avatar makeup simulation and generative artificial intelligence virtual try-on tools for perceived social validation, unfavorable appearance comparisons, and negative body image, mood, and self-esteem. The review software systems leveraged for article screening and quality evaluation include AMSTAR, CADIMA, DistillerSR, Eppi-Reviewer, JBI SUMARI, Litstream, PICO Portal, and SWIFT-Active Screener. The case studies cover Airbrush, B612, BeautyPlus, Evoto, FaceApp, Facetune, Fotor, GlamAR, Perfect365, PortraitPro, PrettyUp, SODA, Ulike, Vivid Glam, Wondershare DemoCreator, and YouCam.

Keywords: visual sentiment; affective computing; emotion recognition; digital beauty; facial avatar makeup simulation; generative artificial intelligence virtual try-on

How to cite: Popescu, G. H., Khamis, A. D., Erokhin, V., Iacob, S. E., Ujang, R., and Boajă, D. M. (2025). “Visual Sentiment and Affective Computing Algorithms, Deep Learning-based Multimodal Emotion Recognition and Automated Digital Beauty Technologies, and 3D Machine Learning-based Facial Avatar Makeup Simulation and Generative Artificial Intelligence Virtual Try-on Tools for Perceived Social Validation, Unfavorable Appearance Comparisons, and Negative Body Image, Mood, and Self-Esteem,” Journal of Research in Gender Studies 15(2): 65–75. doi: 10.22381/JRGS15220255.

Received 8 July 2025 • Received in revised form 20 December 2025
Accepted 28 December 2025 • Available online 30 December 2025