Real Time Mood Detection on Music Streaming Platforms

The facial expressions of a user can be used to identify their emotional state or mood. The device's camera can also be used to capture these expressions as they are being displayed on the live stream. Machine learning is a promising tool for learning about human emotions. One of the most common methods for developing a trained model is through the MobileNet model with the Keras framework. The practice of determining a person's emotions via a variety of facial expressions and visual signals is known as emotion detection. Since deep learning has become more and more popular, this discipline has expanded rapidly. Additionally, a lot of hitherto unimagined applications have been made possible by emotion recognition. Music is one of the things that is closely related to feelings. A person experiencing a certain mood may seek for a song that evokes the same emotion in them. Our emotion detection model allows us to associate these emotions with a music player that plays music in time with user experiences. The model we developed consists of two convolutional neural network (CNN) models: a global average pooling (GAP) model and a five-layer model.