Modeling Visual Aesthetics, Emotion, and Artistic Style

Abstract

This review examines Modeling Visual Aesthetics, Emotion and Artistic Style, edited by James Z. Wang and Reginald B. Adams, highlighting its interdisciplinary engagement with psychology, computer vision, art history, and machine learning in exploring how computational systems interpret emotion, aesthetic judgment, and artistic style. The review outlines recent developments in emotion modeling, algorithmic bias detection, feminist critiques of computational frameworks and the digital analysis of fine art. It emphasizes the editors’ focus on ethical concerns, particularly gender and racial biases embedded in datasets, while also drawing attention to unresolved issues related to structural inequalities in cultural production and emerging surveillance technologies. Overall, the book is assessed as an important contribution to contemporary debates on the interaction between technology, emotion and artistic interpretation within machine learning research.