Wide & Deep Learning for Judging Student Performance in Online One-on-one Math Classes
This addresses the challenge of scalable, automated evaluation for online math education providers, though it appears incremental as it applies an existing Wide & Deep architecture to a new educational domain.
The paper tackles the problem of automating student performance assessment in online one-on-one math classes by developing a Wide & Deep learning framework that processes noisy classroom conversation data, achieving superior results in predicting student mastery levels across multiple evaluation metrics.
In this paper, we investigate the opportunities of automating the judgment process in online one-on-one math classes. We build a Wide & Deep framework to learn fine-grained predictive representations from a limited amount of noisy classroom conversation data that perform better student judgments. We conducted experiments on the task of predicting students' levels of mastery of example questions and the results demonstrate the superiority and availability of our model in terms of various evaluation metrics.