Xue Zhang

Colleges and universities are in an important position to train builders and successors of the socialist cause whilst promoting quality education. Mental health education is an important foundation and condition for comprehensively improving students' overall quality. This research explores adjustment methods for college students' mental health based on virtual reality under the background of positive psychology. It discusses the importance of system requirements analysis in the software development process, analyzes the system's functional requirements, safety requirements, and software and hardware requirements, and uses the Apriori algorithm to explore the influencing factors of college students' mental health. Based on the system engineering method and using the data mining clustering method undertake detailed analysis and research on the mental health of college students, it then designs an anomaly mining algorithm based on clustering to quickly find anomalous data health problems. The interface design of the system is concise and the operation is simple. Users can conveniently input, query, and count information according to the various controls on the interface, which fully embodies human-oriented characteristics. Exploration of the characteristics of students' frequent Internet access ensures the efficiency, accuracy, and comprehensiveness of the evaluation and consultation work, facilitating psychological counseling for teachers and students, and saving paper. By establishing a data mining model, mining the database, and learning about different student groups and their respective characteristics, we discuss our research on student psychology and summarize the mental health status and gender, adaptation and anxiety, introversion, emotionality, and calmness of college students. We also consider the relationship between sex, negative, and courage. Using positive psychology theory, we examine the positive experiences of students and interconnected qualities, to build a mental health practice system. In the experiment, the happiness index evaluation of the virtual reality treatment system group was significant, P = 0.002 < 0.05. Mental health education plays an important role in cultivating the healthy psychology of college students, developing their psychological potential, enhancing their adaptability, and improving their personality. This analysis based on actual data provides a reliable basis for psychological educators to improve the efficiency and effectiveness of school psychological counseling and to facilitate schools in establishing new methods of early prevention and intervention for psychological disorders, enabling institutions to create a healthy atmosphere for college students.

Starting from the perspective of social perception of voluntary employee green behavior and studies on the attribution of VEGB, we explore the phenomenon that employees can show different perceptions and behavioral responses to VEGB according to their attribution to VEGB. We served to examine the hypotheses. The results of a two-wave study show that when employees believe VEGB is motivated by instrumental concerns, VEGB is more likely to evoke a low level of warmth and competence, which produces less green advocacy. However, if employees believe VEGB is motivated by moral reasons, VEGB is more likely to prompt more warmth and competence perceptions and elicit greener advocacy from employees. In addition, theoretical and practical contributions are discussed.

Multilevel item response theory models are used widely in educational and psychological research. This type of modeling has two or more levels, including an item response theory model as the measurement part and a linear-regression model as the structural part, the aim being to investigate the relation between explanatory variables and latent variables. However, the linear-regression structural model focuses on the relation between explanatory variables and latent variables, which is only from the perspective of the average tendency. When we need to explore the relationship between variables at various locations along the response distribution, quantile regression is more appropriate. To this end, a quantile-regression-type structural model named as the quantile MLIRT model is introduced under the MLIRT framework. The parameters of the proposed model are estimated using the Gibbs sampling algorithm, and comparison with the original MLIRT model is conducted via a simulation study. The results show that the parameters of the Q-MLIRT model could be recovered well under different quantiles. Finally, a subset of data from PISA 2018 is analyzed to illustrate the application of the proposed model.