Affective Model

Affective modeling aims to computationally represent and predict human emotions, focusing on mapping observable manifestations (facial expressions, physiological signals, text) to affective states like valence and arousal. Current research emphasizes the use of large language models (LLMs) and deep learning architectures, including contrastive learning and recurrent neural networks, to improve accuracy and address challenges like personalization and privacy. This field is significant for advancing human-computer interaction, improving mental health interventions (e.g., for autism), and enhancing the ethical design of AI systems that interact with humans.