Multimodal learning analytics for precision labor education: an AI and big-data-driven approach

Abstract

In the context of education reform in the new era, labor education, as an important part of the comprehensive development of the education system, urgently needs to break through the limitations of the traditional teaching mode to achieve accurate and personalized teaching. Aiming at the practical characteristics of labor education scenarios, this study constructs a precision teaching analysis framework based on multimodal data fusion including classroom images, operation videos and assignment texts, and clarifies the application path of visual information in teaching effect prediction. The potential and limitations of the application of artificial intelligence and machine learning in formative assessment are discussed. This study concludes that although the algorithms of artificial intelligence and big data analysis have improved the feedback speed and accuracy of the automated assessment system, its application value for the evaluation of students' deep learning and ability development is still limited, and the application of artificial intelligence and big data technology in accurate teaching of labor education can not only improve the teaching efficiency and students' participation, but also provide technical support for the fairness and sustainable development of education. This study provides a theoretical basis and practical reference for the intelligent development in the field of labor education.