A Novel Adaptive Affective Cognition Analysis Model for College Students Using a Deep Convolution Neural Network and...

Area of Science:

• Psychology
• Computer Science
• Education

Background:

• COVID-19 has increased employment and academic pressures on college students, leading to mental health issues like anxiety and depression.
• Traditional methods for assessing affective cognition in students are often slow, rely on single data sources, and are prone to errors.
• Smart campus initiatives offer rich data resources for developing more effective mental health assessment tools.

Purpose of the Study:

• To develop a novel adaptive affective cognition analysis model for college students.
• To overcome the limitations of traditional assessment methods by utilizing deep learning and multisource data.
• To improve the accuracy and efficiency of identifying and addressing psychological distress in students.

Main Methods:

• Construction of a multisource dataset incorporating access control, network, and learning data from smart campus platforms.
• Classification of data into image and text categories for analysis.
• Application of Convolutional Neural Network (CNN) models to extract psychological characteristics from the data.

Main Results:

• The developed model demonstrated significantly increased accuracy in assessing affective cognition.
• The model effectively leverages the heterogeneity and comprehensiveness of multisource data.
• Simulation tests confirmed the viability and effectiveness of the proposed deep learning approach.

Conclusions:

• The novel deep learning-based affective cognition analysis model offers a more accurate and efficient method for college student mental health assessment.
• This approach has broad potential applications within modern smart campus environments.
• Improved affective cognition analysis can contribute to better student well-being and overall campus development.