Question Difficulty Consistent Knowledge Tracing

Guimei Liu, Huijing Zhan, Jung-jae Kim

Keywords: knowledge tracing; learning activities

Abstract: Knowledge tracing aims to estimate knowledge states of students based on their historical learning activities. Many deep learning models have been developed for knowledge tracing with impressive performance. Early works like DKT use skill IDs and student responses only. Recent works also incorporate questions IDs into their models and achieve much improved performance. However, predictions made by these models are thus on specific questions, and it is not straightforward to translate them to estimation of students' knowledge states over skills. In this paper, we propose to replace question IDs with question difficulty levels in deep knowledge tracing models, which transforms the knowledge tracing problem to ``predicting whether a student can answer any question of a given skill at a given difficulty level correctly". The predictions made by our model can be more readily translated to students' knowledge states over skills. Furthermore, by using question difficulty levels to replace question IDs, we can also alleviate the cold-start problem in knowledge tracing as online learning platforms are updated frequently with new questions. We further use two techniques to smooth the predicted scores. One is to combine embeddings of nearby difficulty levels using a Hann function. The other is to constrain the predicted probabilities to be consistent with question difficulty levels by imposing a penalty if they are not consistent. We conduct extensive experiments to study the performance of the proposed model. Our experiment results show that our model outperforms latest knowledge tracing models in terms of both AUC/RMSE and consistency with question difficulty levels.

Track: Web Mining and Content Analysis

Submission Guidelines Scope: Yes

Submission Guidelines Blind: Yes

Submission Guidelines Format: Yes

Submission Guidelines Limit: Yes

Submission Guidelines Authorship: Yes

Student Author: No

Submission Number: 1593