Research Article
Classifying Evaluation Method of Innovative Teachers’ Teaching Ability Based on Multi Source Data Fusion
@INPROCEEDINGS{10.1007/978-3-031-50571-3_12, author={Fanghui Zhu and Shu Fang}, title={Classifying Evaluation Method of Innovative Teachers’ Teaching Ability Based on Multi Source Data Fusion}, proceedings={Multimedia Technology and Enhanced Learning. 5th EAI International Conference, ICMTEL 2023, Leicester, UK, April 28-29, 2023, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2024}, month={2}, keywords={Multi-Source Data Fusion Innovative Teachers Teaching Ability Classification Evaluation}, doi={10.1007/978-3-031-50571-3_12} }- Fanghui Zhu
Shu Fang
Year: 2024
Classifying Evaluation Method of Innovative Teachers’ Teaching Ability Based on Multi Source Data Fusion
ICMTEL
Springer
DOI: 10.1007/978-3-031-50571-3_12
Abstract
Massive teaching ability data leads to a large difference between the evaluation index and the actual index. Therefore, a classification evaluation method for innovative teachers’ teaching ability based on multi-source data fusion is proposed. Integrate innovative teachers’ teaching data feature level multi-source data to generate scene data that can accurately describe learners’ learning characteristics. The model of teachers’ practical teaching ability is constructed, the information flow expressing the constraint parameters is obtained, and the convergent solution of teaching ability evaluation is calculated. Use the analytic hierarchy process to calculate the data similarity, and use the quantitative recursive analysis method to describe the form of evaluation data. Integrate the five dimensional characteristic data of learner situation, time situation, location situation, equipment situation, event situation and learning scene, build an evaluation model based on multi-source data fusion, and achieve the classified evaluation of innovative teachers’ teaching ability. The experimental results that the maximum values of the teaching skill index, learning input index and learning harvest index of this method are 9.8, 9.6 and 9.2 respectively, which shows that the classification evaluation results are accurate.
