| dc.description.abstract | Mental health challenges among university students have become a significant concern,
with academic workload, social isolation, and personal issues being major contributing
factors to mental disorders. This review aims to analyze existing studies on wearable
technologies and affective computing to detect mental disorders among university
students and identify the primary factors contributing to these issues. The review
explores concepts such as affective computing, a key area of Human-Computer
Interaction (HCI), and the application of machine learning algorithms, including Support
Vector Machines (SVM) and Deep Neural Networks, for effective data processing and
feature extraction. Following the PRISMA 2020 guidelines for meta-analysis, the study
includes research sourced from various academic databases. The findings indicate that
academic workload is the most significant stressor for university students, particularly
those living in boarding houses. Additionally, inadequate sleep exacerbates negative
emotions, highlighting the importance of features such as sleep tracking and heart rate
monitoring to track physiological signals. Behavioral patterns, such as reduced SMS
usage among highly stressed individuals, were also identified as potential indicators of
emotional well-being. By synthesizing diverse approaches to managing mental health,
the study identifies gaps in current capabilities, such as the contextual challenges
of distance learning, and limitations like the high power consumption of wearable
devices. These insights are categorized under themes of affective computing and
wearable technologies. The study emphasizes the critical role of wearable technologies
and affective computing in accurately diagnosing and monitoring mental health. The
implications provide strategic guidance for future research to develop optimal solutions
for managing the mental health of university students. | en_US |
