Level of agreement between emotions generated by Artificial Intelligence and human evaluation: a methodological proposal

TL;DR

This study evaluates how well AI-generated images evoke emotions comparable to human responses, using a methodological approach with artistic landscapes and observer classification to measure agreement levels.

Contribution

It introduces a novel method for assessing the alignment between AI-generated emotional images and human emotional perception.

Findings

Good agreement for negative emotions

Higher consistency among observers for certain emotions

Subjectivity remains a key factor in emotional evaluation

Abstract

Images are capable of conveying emotions, but emotional experience is highly subjective. Advances in artificial intelligence have enabled the generation of images based on emotional descriptions. However, the level of agreement between the generative images and human emotional responses has not yet been evaluated. To address this, 20 artistic landscapes were generated using StyleGAN2-ADA. Four variants evoking positive emotions (contentment, amusement) and negative emotions (fear, sadness) were created for each image, resulting in 80 pictures. An online questionnaire was designed using this material, in which 61 observers classified the generated images. Statistical analyses were performed on the collected data to determine the level of agreement among participants, between the observer's responses, and the AI-generated emotions. A generally good level of agreement was found, with better results for negative emotions. However, the study confirms the subjectivity inherent in emotional evaluation.