Deep learning is a fast-growing area that has an ever-increasing number of application domains. Recommendation systems are one such domain where deep learning offers promising results. Their use ranges from obtaining user feedback from reviews and comments on social media through sentiment analysis to the creation of models that capture the complex relationships between users and items, generally through attribute embedding. Among the many deep learning techniques are graph neural networks (GNN), which are lately gaining a significant amount of importance in recommendation systems for their ability to represent relationships. However, a major problem of GNN and, generally, all deep learning approaches, is the high sensitivity to data biases. Therefore, facing this drawback is a major concern for researchers in this area. This Special Issue provides an opportunity to address the challenges of today's deep learning-based recommender systems through the presentation of new research advances. The topics of interest include, but are not limited to, the following:

Deep learning methods for recommender systems;
GNN-based recommendation methods;
Implicit user feedback from sentiment analysis;
Bias and fairness in recommender systems based on deep learning;
Multi-objective recommendations based on deep learning;
Deep learning techniques for session-based recommendations;
Deep learning approaches for context-aware recommender systems.