This article investigates the application and research progress of eye tracking, electroencephalography (EEG), and facial expression recognition technologies in the assessment of mental health among college students. Eye tracking records changes in students’ visual behavior, revealing their attention allocation, emotional fluctuations, and cognitive load; EEG technology captures the electrical activity of the brain and provides information on neurophysiological states, especially showing high sensitivity in detecting psychological problems such as anxiety and depression; Facial expression recognition further improves the accuracy of emotion recognition by analyzing changes in facial expressions. This article analyzes the advantages and limitations of these technologies and points out the shortcomings of a single technology in mental health assessment. To overcome these limitations, multimodal data fusion technology has been proven to be able to more comprehensively and accurately assess students’ psychological states. By combining eye movement, EEG, and facial expression recognition data, research has shown that this fusion can improve the accuracy and effectiveness of mental health assessment, providing more effective psychological assessment methods for college students.