A Self Attentive model for Knowledge Tracing

By Shalini Pandey, George Karypis. Educational Data Mining, 2019

539 citations recorded by the source corpus.

Knowledge tracing is the task of modeling each student's mastery of knowledge concepts (KCs) as (s)he engages with a sequence of learning activities. Each student's knowledge is modeled by estimating the performance of the student on the learning activities. It is an important research area for providing a personalized learning platform to students. In recent years, methods based on Recurrent Neural Networks (RNN) such as Deep Knowledge Tracing (DKT) and Dynamic Key-Value Memory Network (DKVMN) outperformed all the traditional methods because of their ability to capture complex representation of human learning. However, these methods face the issue of not generalizing well while dealing with sparse data which is the case with real-world data as students interact with few KCs. In order to address this issue, we develop an approach that identifies the KCs from the student's past activities that are \textit{relevant} to the given KC and predicts his/her mastery based on the relatively few KCs that it picked. Since predictions are made based on relatively few past activities, it handles the data sparsity problem better than the methods based on RNN. For identifying the relevance between the KCs, we propose a self-attention based approach, Self Attentive Knowledge Tracing (SAKT). Extensive experimentation on a variety of real-world dataset shows that our model outperforms the state-of-the-art models for knowledge tracing, improving AUC by 4.43% on average.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/0abdc7c7c6950a4a5bc6c93cf78d320d6c969152

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing (2020, methodology): “This method follows the attention mechanism of SAKT [14] and EKT [8].”
Knowledge Tracing: A Survey (2022, methodology): “3 Attentive Knowledge Tracing Models Following the Transformer architecture [110], several works [21, 36, 79, 80, 99] have attempted to incorporate an attention mechanism into KT models.”
Context-Aware Attentive Knowledge Tracing (2020, methodology): “We compare AKT against several baseline KT methods, including BKT+ [35], DKT, DKT+ (which is an improved version of DKT with regularization on prediction consistency [34]), DKVMN [36], and the recently proposed self-attentive KT (SAKT) method [18], which uses an attention mechanism that can be viewe”
MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education (2021, methodology): “Predicting students’ next question correctness as a KT task is, for instance, well studied [4, 14, 15, 18, 28] but these solutions tend to rely on highdimensional sequential data.”