Student Dropout Prediction (SDP) is pivotal in mitigating withdrawals in Massive Open Online Courses. Previous studies generally modeled the SDP problem as a binary classification task, providing a single prediction outcome. Accordingly, some attempts introduce survival analysis methods to achieve continuous and consistent predictions over time. However, the volatility and sparsity of data always weaken the models’ performance. Prevailing solutions rely heavily on data pre-processing independent of predictive models, which are labor-intensive and may contaminate authentic data. This paper proposes a Survival Analysis based Volatility and Sparsity Modeling Network (SAVSNet) to address these issues in an end-to-end deep learning framework. Specifically, SAVSNet smooths the volatile time series by convolution network while preserving the original data information using Long-Short Term Memory Network (LSTM). Furthermore, we propose a Time-Missing-Aware LSTM unit to mitigate the impact of data sparsity by integrating informative missingness patterns into the model. A survival analysis loss function is adopted for parameter estimation, and the model outputs monotonically decreasing survival probabilities. In the experiments, we compare the proposed method with state-of-the-art methods in two real-world MOOC datasets, and the experiment results show the effectiveness of our proposed model.
As the core of the Knowledge Tracking (KT) task, assessing students' dynamic mastery of knowledge concepts is crucial for both offline teaching and online educational applications. Since students' mastery of knowledge concepts is often unlabeled, existing KT methods focus on predicting students' responses to practices. However, purely predicting student responses without imposing specific constraints on hidden concept mastery values does not guarantee the accuracy of these intermediate values as concept mastery values. To address this issue, we propose a principled approach called Counterfactual Monotonic Knowledge Tracing (CMKT), which builds on the implicit paradigm described above by using a counterfactual assumption to constrain the evolution of students' mastery of knowledge concepts. Specifically, CMKT first assesses students' knowledge concept mastery value based on their historical practice sequences. Then, CMKT sets the answer of the most recent practice as the opposite of the actual answer and, based on this counterfactual answer, assesses the student's corresponding counterfactual knowledge mastery value. During the model training process, CMKT constrains the update of the student's knowledge states by ensuring that the two types of knowledge mastery values of students satisfy a fundamental educational theory, the monotonicity theory, to provide specific semantics for the assessed mastery values by the model. Finally, extensive experiments on five datasets demonstrate the superiority of CMKT over baseline models.
Knowledge tracing (KT) aims to predict students' responses to practices based on their historical question-answering behaviors. However, most current KT methods focus on improving overall AUC, leaving ample room for optimization in modeling sequences of excessive or insufficient lengths. As sequences get longer, computational costs will increase exponentially. Therefore, KT methods usually truncate sequences to an acceptable length, which makes it difficult for models on online service systems to capture complete historical practice behaviors of students with too long sequences. Conversely, modeling students with short practice sequences using most KT methods may result in overfitting due to limited observation samples. To address the above limitations, we propose a model called Sequence-Flexible Knowledge Tracing (SFKT). Specifically, to flexibly handle long sequences, SFKT introduces a total-term encoder to effectively model complete historical practice behaviors of students at an affordable computational cost. Additionally, to improve the prediction accuracy of students with short practice sequences, we introduce a contrastive learning task and data augmentation schema to improve the generality of modeling short sequences by constructing more learning objectives. Extensive experimental results show that SFKT achieves significant improvements over multiple benchmarks, demonstrating the value of exploring the modeling of sequences of excessive or insufficient lengths. Our code is available at https://github.com/zmy-9/SFKT.