As the rapid development of computer music, the technique for recognizing the emotion of music also have many progresses. After the brief introduction of the history of computer music, this paper mainly discusses about the current existing machine learning models for the emotion recognition in music. The complexity of emotion has been emphasized in this paper for several reasons. In addition, by comparison different models, this paper summarizes common features, metrics and steps used in music emotion analyzation. Moreover, this study finds out the limitations and disadvantages of different classifications and feature extracting method for different models, pointing out the living problems, e.g., the difficulty of emotion recognition for experimental music. To sum up, this paper summarizes and analyzes the primary studying in the field of music emotion recognition, offering a guideline for implementations of different machine learning approaches in the field. These results shed light on paving a path for further exploration of emotion recognition in computer music.