In this new era that is full of social changes, ongoing economic transformation, an abundance of information resources, and a fast pace of life, the pressure that people feel to compete with one another is also increasing day by day. Because of the vast differences in people’s states of consciousness and worldviews, interpersonal relationships have become increasingly difficult to navigate. Students in higher education institutions will eventually emerge as the dominant demographic in society. Their mental health has a significant bearing on all aspects of life, including learning and future growth. An objective condition that must be met in order to guarantee that the next generation of talent will have a high level of overall quality is the improvement of the mental health of college students (CSMH) in the new era. One component of public health is the emotional well-being of students in higher education. The state of the public’s health is consistently ranked among the most urgent problems facing modern society. However, there is not much hope for the Chinese CSMH. In order to effectively manage their mental health, a variety of educational institutions, including colleges and universities, have proposed a large number of management strategies for CSMH. The vast majority of these strategies are not targeted, and they do not offer a variety of management strategies that are based on the many different psychological states. It is necessary to first be able to accurately predict the mental health status of each individual college student in order to achieve the goal of improving the mental health management of students attending colleges and universities. This study proposes using a multi-view K-means algorithm, abbreviated as MvK-means, to analyze the CSMH’s data on mental health. This is possible because the data can be obtained from multiple perspectives. This paper presents a multi-view strategy as well as a weight strategy in light of the fact that each point of view contributes in its own unique way. Different weight values should be assigned to each view’s data, which will ultimately result in an improved evaluation effect of the model. The findings of the experiments indicate that the model that was proposed has a beneficial impact on the analysis of the data pertaining to the mental health of college students.

The emotional well-being of college students is of utmost significance. The psychological states of college students who are on the verge of entering the social work field form the key factor that directly influences the quality of social construction because these students constitute the primary driving force in the field. On the other hand, the overwhelming amount of schoolwork, the intense level of competitiveness, and the undeveloped psychological qualities of college students are the primary contributors to their mental health problems. Currently, an increasing number of college students are struggling with mental health issues, which will have a significant impact on the growth of families and schools and the future construction of the nation. In this paper, deep features and a multiview fuzzy clustering technique are presented, as well as a mental health assessment model (CNN-MV-MEC) that is proposed for college students. The primary purpose of this research is to determine the mental state of the input sample by classifying and identifying an EEG that was acquired through the application of CNN-MV-MEC. If a certain number of samples are found to be in negative emotional states on a regular basis or for an extended period of time, this indicates that the sample most likely contains individuals who struggle with mental health issues. At this point in time, university officials are in a position to implement follow-up mental health management actions based on the outcomes of the model evaluation process. The primary contributions of this study are as follows. First, to extract the deep features from the given dataset, this paper makes use of a traditional convolutional neural network (CNN). In the second step, a classification model is trained using a multiview maximum entropy clustering (MV-MEC) technique. In the final step, the input test data are categorized by employing the trained classification model to determine the emotional state of the sample. The SEED dataset is used as the training data for the mental health assessment model proposed in this paper. Thus, the performance of the model can be evaluated. Model comparison experiments demonstrate that the proposed approach yields more accurate results than competing methods when assessing the mental health of college students.