Modeling Induced Pleasure through Cognitive Appraisal Prediction via Multimodal Fusion

TL;DR

This paper presents a novel multimodal computational model that predicts video-induced pleasure by integrating cognitive appraisal theory with transformer-based architectures, improving interpretability and addressing key challenges in affective computing.

Contribution

It introduces an innovative framework combining data-driven and cognitive theory-driven methods, utilizing transformers and fuzzy models for interpretable multimodal affect prediction.

Findings

Achieved a peak accuracy of 0.6624 in predicting pleasure levels.

Effectively captures inter- and intra-modal dynamics related to pleasure.

Enhances model explainability beyond traditional statistical methods.

Abstract

Multimodal affective computing analyzes user-generated social media content to predict emotional states. However, a critical gap remains in understanding how visual content shapes cognitive interpretations and elicits specific affective experiences such as pleasure. This study introduces a novel computational model to infer video-induced pleasure via cognitive appraisal variables. The proposed model addresses four challenges: (1) noisy and inconsistent human labels, (2) the semantic gap between "positive emotions" and "pleasure," (3) the scarcity of pleasure-specific datasets, and (4) the limited interpretability of existing black-box fusion methods. Our approach integrates data-driven and cognitive theory-driven methods, using cognitive appraisal theory and a fuzzy model within an innovative framework. The model employs transformer-based architectures and attention mechanisms for fine-grained multimodal feature extraction and interpretable fusion to capture both inter- and intra-modal dynamics associated with pleasure. This enables the prediction of underlying appraisal variables, thereby bridging the semantic gap and enhancing model explainability beyond conventional statistical associations. Experimental results validate the efficacy of the proposed method in detecting video-induced pleasure, achieving a peak accuracy of 0.6624 in predicting pleasure levels. These findings highlight promising implications for affective content recommendation, intelligent media creation, and advancing our understanding of how digital media influences human emotions.