Analyzing the Relationships of Psychological Symptoms in the SCL-90 Using Genetic Algorithms and Association Rule Mining

To improve the efficiency of processing SCL-90 data with association rules, this study integrates genetic algorithms with association rule mining techniques to analyze data from the SCL-90. The goal is to identify potential patterns and associations in psychological health issues. The SCL-90 is a widely used tool for assessing psychological symptoms and distress levels, consisting of 90 items that cover multiple dimensions such as obsessive-compulsive symptoms, anxiety, and depression. By employing genetic algorithms for preprocessing and optimizing the SCL-90 data, representative and distinctive feature subsets are selected. Genetic algorithms simulate the processes of natural selection, crossover, and mutation to identify optimal feature combinations, thereby enhancing the efficiency and effectiveness of association rule mining. The selected data is then analyzed using association rule mining techniques to generate rules with high support and confidence, revealing potential links between different psychological symptoms. The combination of genetic algorithms and association rule mining not only improves data processing and pattern discovery efficiency but also provides valuable insights for psychological health assessment and intervention.