Scholarlink

<p>Traditional educational evaluation models cannot comprehensively evaluate students' learning effects and learning abilities in advance, and it is also difficult to track the development and changes of students' abilities in the learning process in real time, and cannot accurately recommend appropriate knowledge and learning methods. In order to improve the data processing effect and functionality of educational evaluation model, this paper proposes an FR-Apriori algorithm. By combining the MapReduce framework, the FR-Apriori algorithm can distribute calculations on multiple nodes, which improves the overall running efficiency of the algorithm. Moreover, this paper builds FR-APRIORI-M-SAKT model on the basis of FR-Apriori algorithm to further improve the data processing efficiency and functionality of the model through two-stage method of data evaluation and knowledge recommendation. Combined with the experimental results, it can be seen that FR-Apriori algorithm has higher efficiency and speed in the processing of educational review data. Because invalid rules can be effectively eliminated in algorithm processing, it can meet the processing needs of college educational evaluation data. Therefore, for teaching evaluation and knowledge recommendation in colleges and universities, the FR-APRIORI-M-SAKT model constructed in this paper can meet the actual needs.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Intelligent data analysis based on natural language processing technology in educational evaluation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年5月10日

查看全文
  • Ruili Zheng

摘要

Traditional educational evaluation models cannot comprehensively evaluate students' learning effects and learning abilities in advance, and it is also difficult to track the development and changes of students' abilities in the learning process in real time, and cannot accurately recommend appropriate knowledge and learning methods. In order to improve the data processing effect and functionality of educational evaluation model, this paper proposes an FR-Apriori algorithm. By combining the MapReduce framework, the FR-Apriori algorithm can distribute calculations on multiple nodes, which improves the overall running efficiency of the algorithm. Moreover, this paper builds FR-APRIORI-M-SAKT model on the basis of FR-Apriori algorithm to further improve the data processing efficiency and functionality of the model through two-stage method of data evaluation and knowledge recommendation. Combined with the experimental results, it can be seen that FR-Apriori algorithm has higher efficiency and speed in the processing of educational review data. Because invalid rules can be effectively eliminated in algorithm processing, it can meet the processing needs of college educational evaluation data. Therefore, for teaching evaluation and knowledge recommendation in colleges and universities, the FR-APRIORI-M-SAKT model constructed in this paper can meet the actual needs.