Filtering Influential Features for Adolescent Positive Mental Health
- Resource Type
- Conference
- Authors
- Yi, Cao; Shimin, Cai; Tao, Zhou
- Source
- 2023 20th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP) Wavelet Active Media Technology and Information Processing (ICCWAMTIP), 2023 20th International Computer Conference on. :1-5 Dec, 2023
- Subject
- Computing and Processing
Robotics and Control Systems
Signal Processing and Analysis
Machine learning algorithms
Filtering
Anxiety disorders
Mental health
Information processing
Media
Feature extraction
Adolescent positive mental health
Feature selection
Heuristic method
Data mining
Machine learning
- Language
- ISSN
- 2576-8964
Adolescents' positive mental health is deeply associated with their growth. Identifying the factors that contribute to the positive mental health of junior and senior high school students is crucial for supporting youth development in the long run. Leveraging questionnaire data, this paper utilizes machine learning algorithms and fusion methods for feature selection to examine the factors that influence the onset of adolescent positive mental health. The influential features are ranked by importance. Then, machine learning algorithms in a heuristic form are employed to assess the predictive power of the fused features. The best f1-score of the classifiers reaches 0.844. It illustrates the effectiveness of feature filtering and provides valuable references for educational administrators to potential interventions.