Research on the influence of mental health on college students' employment based on fuzzy clustering techniques

With the increasingly severe unemployment situation, the competition among undergraduates in employment is becoming more and more fierce, and the psychological pressure of undergraduates in employment is also growing. Undergraduates have a huge psychological gap because of the conflict between their ideals in employment and the specific social reality. This gap puts undergraduates in a state of psychological imbalance, often accompanied by anxiety, inferiority, self-denial, and other mentalities. It is very necessary to deeply explore the internal relationship between the position of the enterprise and the comprehensive quality of the employed students, and on this basis, it is necessary to construct an analysis mechanism for the matching of people and posts based on the portrait of students and the information of job requirements. Taking these points into account, in this study, we investigated the use of fuzzy clustering algorithms in the evaluation of psychological health in undergraduate students. Student psychological pressure is on the rise as a result of the increasingly competitive work landscape, prompting the development of novel early detection and intervention strategies. We proposed using fuzzy clustering methods to efficiently classify students according to their mental health. For this purpose, we collected many psychologically relevant characteristics, from different students using a SCL-90 symptom checklist. After the data collection, the preprocessing and feature extraction were carried out. The preprocessed data is then used for the students' psychological health analysis. The students are given degrees of membership based on their distance from cluster centroids, allowing them to simultaneously belong to many clusters (good, normal, mild abnormality, and severe abnormality). To maximize the performance of our proposed model to divide students into various mental health groups with flexible and exact membership degrees, we fine-tuned the membership function by iteratively adjusting parameters. The resulting our proposed method offers a flexible and precise way to grasp the mental health landscape, opening up a promising new direction for specialized assistance and interventions. Our research adds to the expanding body of knowledge on data-driven approaches to mental health evaluation by presenting a novel application of fuzzy clustering in the context of student well-being assessment.