期刊：
International Journal of Information and Communication Technology,2025年26(2):36-50 ISSN：1466-6642
作者机构：
[Ninghua Huang] School of Marxism, Changsha University of Science and Technology, Changsha 410011, China;[Baoqin Gong] School of Marxism, Xi'an Siyuan University, Xi'an 710038, China
关键词：
deep learning;machine learning;mental health;college student psychology.
摘要：
This article proposes a method for monitoring the mental health status of college students based on machine learning models. By integrating multidimensional data such as psychological assessment questionnaires and daily behaviour data, and using machine learning techniques such as support vector machine, random forests, and deep learning algorithms, a prediction model that can efficiently identify the mental health status of college students is constructed. This model improves the quality of data and the accuracy of model predictions through steps such as feature engineering and data preprocessing. This article used real datasets from multiple universities for experimental testing, and the results showed that the method performed well in multiple evaluation indicators such as accuracy, recall, and F1 score, demonstrating strong practicality and promotional value.
作者机构：
[Zhou, Yongxu; Bian, Junfeng; Fang, Yu; Gao, Fugang; Ran, Buqing; Deng, Youjun; Li, Xin; Huang, Tianjing] Changsha Univ Sci & Technol, Sch Marxism, Changsha, Peoples R China.;[Wu, Yajun] Hunan Normal Univ, Sch Educ Sci, Changsha, Peoples R China.;[Bian, Junfeng] Chinese Acad Sci, Inst Psychol, Beijing, Peoples R China.;[Bian, Junfeng] Univ Chinese Acad Sci, Dept Psychol, Beijing, Peoples R China.;[Bian, Junfeng] Hunan Prov Social Governance Innovat Res Ctr, Changsha, Peoples R China.
通讯机构：
[Bian, JF ] C;Changsha Univ Sci & Technol, Sch Marxism, Changsha, Peoples R China.;Chinese Acad Sci, Inst Psychol, Beijing, Peoples R China.;Univ Chinese Acad Sci, Dept Psychol, Beijing, Peoples R China.;Hunan Prov Social Governance Innovat Res Ctr, Changsha, Peoples R China.
关键词：
Moral conscience;Trust violation;Trust repair;Virtual setting;Real-world setting
摘要：
Trust is a fundamental component of social relationships and a prerequisite for smooth and efficient interactions. However, trust is fragile and easily threatened or broken. Recovering trust as quickly and effectively as possible is a top priority. The current study conducts three experiments (N = 1036) to examine how individuals' moral conscience influenced trust violation and its repair strategies under virtual and real scenarios. In Experiment 1 we aimed to examine the effect of state-based conscience on trust violation, and we found conscience elicited trusting behavior after trust violation. In Experiment 2 we aimed to disclose the impact of trait-based conscience on trust violation in real-world and virtual settings, and we found participants with low conscience levels perceived more serious breaches of trust than those with high levels in the real scenario, only participants with high conscience levels were more likely to trust others, regardless of whether in the virtual or real scenarios. In Experiment 3 we aimed to examine the effect of the influence of conscience on preferences for trust repair strategies in real-world and virtual settings, and we found participants favored the financial compensation strategy in the real scenario but preferred the apology strategy in the virtual scenario, however, participants with high conscience levels took more effective trust repair strategies and thus had a more positive effect on trust recovery after violations. Together, results indicated that moral conscience mattered: higher conscience level diminished the breaches of trust violation and made trust restoration easier, and conscience could predict the effectiveness of different restoration strategies in real scenario.
