Research and Development of a Student Behavior Analysis System Based on Big Data Mining

To enhance the efficacy of student work management, the author advocates for a Big Data-driven student behavior analysis system. This system encompasses various modules, including comprehensive student behavior profiling, comprehensive warning generation, behavior trajectory tracking, big data analysis reporting, and establishment of warning protocols based on student conduct. The coding implementation of the system was streamlined through the adoption of lightweight Java EE development frameworks like Spring MVC and MyBatis. This strategic choice aimed to alleviate repetitive coding tasks, thereby enhancing development efficiency. The test results show that during the nearly 30 day testing cycle, a total of 187 problem orders were discovered, and all issues have been modified so far, with a 100% modification rate and no remaining issues. There are a maximum of 71 problems with moderate severity, 54 serious problems, and relatively few particularly serious and minor problems, with 27 and 32, respectively. In the distribution of bug types, code error problems are the most common, followed by interface optimization and data problems, with more than ten prompts, design defects, and other issues, and the least security related issues. Conclusion: The system operates normally and greatly improves the efficiency of student management in the school.