ETVKT: Enhanced Training Vector for Knowledge Tracing

Knowledge tracing is an effective tool for assessing learners' knowledge mastery status through learning activities. The primary objective of Knowledge tracing is to individualize the practice sequence in order to facilitate efficient acquisition of knowledge concepts by students. In recent years, Knowledge tracing methods based on deep learning has achieved performance beyond traditional models. However, most deep learning models ignore the impact of feature vector training methods on the overall performance of the model. In this paper, we propose a novel Enhanced Training Vector for Knowledge Tracing (ETVKT). ETVKT has an additional contextual text information layer to capture the correlation information between texts. And it employs Temporal Convolutional Network (TCN) as a state extraction layer to mine the learner's knowledge mastery status. Slightly different from the general training process, the encoding vector is directly input into the TCN, thereby enhancing the model's attention towards pivotal information. Finally, the feature vector is decoded using Long Short-term Memory Network. We conduct evaluation experiments on the ASSISTments2009 and ASSISTments2017 datasets. The experimental results demonstrate that the ETVKT model outperforms the existing baseline knowledge tracing model in terms of performance.