In daily life, visual aesthetic experiences often arise from sustained exposure to dynamic stimuli. However, we still have a limited understanding of how aesthetic experiences emerge and continuously change in such situations. In this project, we aim to explore how visual information drives aesthetic appeal and which neural mechanisms contribute to this process. We will collect behavioral data while participants watch the documentary “Home” and continuously rate aesthetic appeal. During these experiments, we will also record eye movements and EEG activity. The chosen documentary features a diverse range of visual contents, from the dance of a whale to forest fires, capturing both pleasing and unpleasing scenes from all around the world. This variety mimics the complexity and vastness of real-life experiences. This is a critical advance over previous studies, which mainly used short video clips or static images. By using a long and diverse movie and continuous ratings, we can now study how aesthetic experiences arise and transform over longer timescales. Our project has two objectives. The first objective is to predict continuous aesthetic ratings and their variations between observers from visual features. For this, we will develop a model that predicts aesthetic ratings based on visual features extracted from a deep neural network trained on scene classification. The second objective is to predict the ratings from participants’ eye gaze patterns and EEG responses. Deriving predictions from oscillatory EEG activity will specifically allow us to dissociate the influence of feedforward and feedback information propagation on perceived aesthetic appeal.