This study aims to explore the correlation between college students’ digital literacy and mental health and proposes a method based on Twin Support Vector Machines (TWSVMs) classification and chi-square validation correlation analysis. First, a group of college students’ digital literacy data was collected by designing and distributing questionnaires. The questionnaire covers multiple aspects such as digital skills, information literacy, and technology application, to comprehensively evaluate the students’ digital literacy level. The collected digital literacy data were classified using TWSVM to obtain the digital literacy assessment results. Next, the electroencephalogram (EEG) signals of the same group were collected, and the EEG signals were subjected to power spectral density (PSD) feature extraction and TWSVM classification model training to obtain the mental health identification results of each student. Finally, after obtaining the digital literacy assessment and mental health identification results, the chi-square validation method was used for correlation analysis to evaluate the linear relationship between the two. Through the analysis, we found that students with higher digital literacy were more likely to have good mental health. In comparison, students with lower digital literacy were more likely to have mental health problems. This study revealed a significant correlation between college students’ digital literacy and mental health, providing theoretical support and practical guidance for educators and mental health professionals. Improving students’ digital literacy will not only help their academic and career development but may also have a positive impact on their mental health, thereby promoting their overall development.