Emotional states can play an important role in the process of decision making. Researchers have demonstrated the impact of emotions on the effectiveness of recommender systems. Affective recommender systems (ARS) or emotion-aware recommender systems (EARS) are usually associated with multidisciplinary research, including artificial intelligence, human factors, mood or emotions, facial expressions, and physiological information with human–computer interaction.

The development of affective recommender systems promotes various research topics, such as user interaction and interfaces, algorithm design and evaluations, computational efficiency, deep learning-based recommendation models, and recommendation explanations. This Special Issue on “Affective Recommender Systems” aims to promote new theoretical models, approaches, algorithms, and applications related to ARS.