Context-Aware Knowledge Tracing Integrated with the Exercise Representation and Association in Mathematics

Y

7

Mathematics Instruction; Teaching Methods; Online Courses; Distance Education; COVID-19; Pandemics; Intelligent Tutoring Systems; Memory; Technical Support; Individualized Instruction; Mathematical Formulas; Correlation; Prediction; Accuracy; Instructional Effectiveness; Computer Software; Mathematics Achievement; Comparative Analysis; Natural Language Processing; Mathematics Tests; Elementary School Students; Foreign Countries

Influenced by COVID-19, online learning has become one of the most important forms of education in the world. In the era of intelligent education, knowledge tracing (KT) can provide excellent technical support for individualized teaching. For online learning, we come up with a new knowledge tracing method that integrates mathematical exercise representation and association of exercise (ERAKT). In the aspect of exercise representation, we represent the multi-dimensional features of the exercises, such as formula, text and associated concept, by using ontology replacement method, language model and embedding technology, so we can obtain the unified internal representation of exercise. Besides, we utilize the bidirectional long short memory neural network to acquire the association between exercises, so as to predict his performance in future exercise. Extensive experiments on a real dataset clearly proved the effectiveness of ERAKT method, they also verified that adding multi-dimensional features and exercise association can indeed improve the accuracy of prediction. [For the full proceedings, see ED615472.]

As Provided

2021

ED615528