Knowledge Tracing Model Research Articles

XKT: Toward Explainable Knowledge Tracing Model With Cognitive Learning Theories for Questions of Multiple Knowledge Concepts

XKT: Toward Explainable Knowledge Tracing Model With Cognitive Learning Theories for Questions of Multiple Knowledge Concepts

DKVMN&MRI: A new deep knowledge tracing model based on DKVMN incorporating multi-relational information.

Knowledge tracing is a technology that models students' changing knowledge state over learning time based on their historical answer records, thus predicting their learning ability. It is the core module that supports the intelligent education system. To address the problems of sparse input data, lack of interpretability and weak capacity to capture the relationship between exercises in the existing models, this paper build a deep knowledge tracing model DKVMN&MRI based on the Dynamic Key-Value Memory Network (DKVMN) that incorporates multiple relationship information including exercise-knowledge point relations, exercise-exercise relations, and learning-forgetting relations. In the model, firstly, the Q-matrix is utilized to map the link between knowledge points and exercises to the input layer; secondly, improved DKVMN and LSTM are used to model the learning process of learners, then the Ebbinghaus forgetting curve function is introduced to simulate the process of memory forgetting in learners, and finally, the prediction strategies of Item Response Theory (IRT) and attention mechanism are used to combine the similarity relationship between learners' knowledge state and exercises to calculate the probability that learners would correctly respond during the subsequent time step. Through extensive experiments on three real-world datasets, we demonstrate that DKVMN&MRI has significant improvements in both AUC and ACC metrics contrast with the latest models. Furthermore, the study provides explanations at both the exercise level and learner knowledge state level, demonstrating the interpretability and efficacy of the proposed model.

Quantum computing enhanced knowledge tracing: Personalized KT research for mitigating data sparsity

With the development of artificial intelligence in education, knowledge tracing (KT) has become a current research hotspot and is the key to the success of personalized instruction. However, data sparsity remains a significant challenge in the KT domain. To address this challenge, this paper applies quantum computing (QC) technology to KT for the first time. It proposes two personalized KT models incorporating quantum mechanics (QM): quantum convolutional enhanced knowledge tracing (QCE-KT) and quantum variational enhanced knowledge tracing (QVE-KT). Through quantum superposition and entanglement properties, QCE-KT and QVE-KT effectively alleviate the data sparsity problem in the KT domain through quantum convolutional layers and variational quantum circuits, respectively, and significantly improve the quality of the representation and prediction accuracy of students’ knowledge states. Experiments on three datasets show that our models outperform ten benchmark models. On the most sparse dataset, QCE-KT and QVE-KT improve their performance by 16.44% and 14.78%, respectively, compared to DKT. Although QC is still in the developmental stage, this study reveals the great potential of QM in personalized KT, which provides new perspectives for solving personalized instruction problems and opens up new directions for applying QC in education.

MLC-DKT: A multi-layer context-aware deep knowledge tracing model

As a fundamental research task for intelligent education, knowledge tracing (KT) aims to trace learners’ dynamic knowledge states and predict their future performance based on their historical response data. However, learners’ cognitive processes cannot be studied in isolation from the context; nevertheless, existing knowledge tracing models mainly use knowledge topology as auxiliary information but do not deeply explore the contextual information of exercises. Thus, an in-depth exploration of multi-layer contextual information in learning scenarios is required, focusing on the cognitive differences among different learners. Furthermore, knowledge tracing models exhibit limited interpretability compared with cognition diagnosis methods integrating educational priors. To address these issues, we propose a multi-layer context-aware deep knowledge tracing (MLC-DKT) model. Specifically, we first present the multi-layer contextual representation method involving knowledge concepts and exercises. In the knowledge state tracing module, we incorporate the learners’ knowledge priors into the attention mechanism to capture the evolution of the learners’ knowledge. Then, we develop a calculation method for the similarity effect among the contextual information, which helps estimate the learners’ knowledge states. In the learning performance prediction module, we introduce the guessing and slipping factors from the cognition diagnosis model to optimize the MLC-DKT model, further improving the performance of the KT model. Finally, we conduct extensive experiments on real-world datasets, demonstrating that the MLC-DKT model provides improved predictions of learner performance. Moreover, the MLC-DKT model realizes contextual awareness from knowledge concepts and exercises, making the predictions more interpretable.

An efficient state-aware Coarse-Fine-Grained model for Knowledge Tracing

Knowledge tracing (KT) is the problem of predicting students’ future performance based on their historical learning records, with primary emphasis on capturing their evolving knowledge states. This predictive capacity enables online education platforms to recommend personalized learning resources and guidance to students who require further attention. By leveraging deep learning techniques, KT models have demonstrated impressive experimental performance in capturing and analyzing the complex interactions between students and exercises. However, most approaches tend to prioritize predictive performance rather than a detailed consideration of how students’ knowledge states evolve over time, resulting in unstable and unexplainable outcomes. To address these limitations, in this paper, we propose an efficient state-aware Coarse-Fine-Grained model for Knowledge Tracing (CFGKT), which aims to facilitate deep tracing of students’ intrinsic knowledge states in their learning processes. Specifically, CFGKT introduces three key innovations: (1) a coarse-grained block that diagnoses students’ proficiency in specific concepts based on their historical performance; (2) a fine-grained block that progressively measures and accumulates students’ experience acquisition from past interactions; and (3) a novel state-fusion attention that selectively integrates both exclusive proficiency and cumulative experience to estimate students’ knowledge states for performance prediction. Numerous experiments on four real-world datasets demonstrate that CFGKT exhibits superior prediction accuracy and interpretability compared to existing KT methods. The code and data are publicly available at https://github.com/hzLu0/CFGKT.

A Genetic Causal Explainer for Deep Knowledge Tracing

Knowledge tracing (KT) has become an increasingly relevant problem in intelligent education services. Deep learning-based knowledge tracing (DLKT) achieves superb performance in terms of prediction accuracy, but it lacks of explainability, which makes us hard to trust or understand models. The previous work on explaining DLKT was mainly based on gradients or attention scores, which is susceptible to spurious correlations, reducing the credibility of the explanation. To address this limitation, in this paper, we propose a causal explanation method based on the genetic algorithm (GA), named Genetic Causal Explainer(GCE), which constructs a causal framework to estimate the attribution of subsequence to the predictions of DLKT models, and a genetic coding system is designed. Further, A multi-strategy initialization method inspired by domain prior knowledge is proposed, and a global empirical matrix is introduced to capture the causal correlation knowledge during the search process across instances, and guiding the mutation operators. The GCE as a post hoc explanation method can generate explanation results without affecting model training, and can be applied to analyze different DLKT models. Experimental results demonstrate the GCE perform better than other explanation methods in terms of accuracy and readability in quantitative assessments. Meanwhile, the GCE also shows good application prospects in mining educational laws and comparing KT models.

Explore Bayesian analysis in Cognitive-aware Key–Value Memory Networks for knowledge tracing in online learning

Knowledge Tracing is a crucial aspect of personalized learning that aims to track the evolving knowledge states of students with respect to one or more concepts. However, existing literature either models knowledge state for each predefined concept separately, potentially overlooking the underlying interrelationships between concepts, or lacks the capability to uncover long-term dependencies within a historical sequence of questions. Furthermore, they have limitations in precisely identifying the mastery level of individual learners for specific concepts. In order to address these problems, we propose a novel deep learning-based knowledge tracing model, named Bayesian Cognitive-aware Key–Value Memory Network (BCKVMN). BCKVMN combines the strengths of Dynamic Key–Value Memory Network (DKVMN), Long Short-Term Memory (LSTM), embedding layer, and Bayesian theory. To capture long-term dependencies in question sequences and contextual information, we extend DKVMN by incorporating a standard LSTM module that integrates cognitive processes observed in human learning. Additionally, we employ an embedding layer to uncover the influence of question difficulty on final predictions. Furthermore, we introduce Bayesian theory to enhance parameter interpretation for the model. To investigate complex representation of human learning, our approach considers not only three distinct learning states during the learning process but also the relationships between underlying concepts and students’ mastery levels for each concept. Experimental evaluations are conducted on the three real-world datasets Algebra200, ASSISTMENTS2009 and ASSISTMENTS2017. The results have demonstrated that the proposed model outperforms state-of-the-art methods (achieving nearly 7% improvement in AUC in some cases) while achieving a better balance between performance and interpretability.

A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models

A Question-centric Multi-experts Contrastive Learning Framework for Improving the Accuracy and Interpretability of Deep Sequential Knowledge Tracing Models

Model-agnostic counterfactual reasoning for identifying and mitigating answer bias in knowledge tracing

Knowledge tracing (KT) aims to monitor students’ evolving knowledge states through their learning interactions with concept-related questions, and can be indirectly evaluated by predicting how students will perform on future questions. In this paper, we observe that there is a common phenomenon of answer bias, i.e., a highly unbalanced distribution of correct and incorrect answers for each question. Existing models tend to memorize the answer bias as a shortcut for achieving high prediction performance in KT, thereby failing to fully understand students’ knowledge states. To address this issue, we approach the KT task from a causality perspective. A causal graph of KT is first established, from which we identify that the impact of answer bias lies in the direct causal effect of questions on students’ responses. A novel COunterfactual REasoning (CORE) framework for KT is further proposed, which separately captures the total causal effect and direct causal effect during training, and mitigates answer bias by subtracting the latter from the former in testing. The CORE framework is applicable to various existing KT models, and we implement it based on the prevailing DKT, DKVMN, and AKT models, respectively. Extensive experiments on three benchmark datasets demonstrate the effectiveness of CORE in making the debiased inference for KT. We have released our code at https://github.com/lucky7-code/CORE.

Meta-path structured graph pre-training for improving knowledge tracing in intelligent tutoring

Knowledge tracing (KT) aims to predict students’ future performance by tracking their learning behaviors in intelligent tutoring systems (ITS). In KT, three main types of entities are involved: students, exercises, and knowledge concepts. Graph structures provide an effective framework for establishing relationships between different entities. However, existing KT methods have neglected complex connections and implicit relational features, thus facing challenges in capturing high-order information in educational data. To this end, this paper proposes MPSG, a Meta-Path Structured Graph method designed to harness high-order information between entities to pre-train informative exercise embeddings for improving KT. Technically, structured by different meta-paths, four relation graphs are derived to establish implicit cross-entity relationships. On each graph, the surrounding neighbors of each node are then obtained through an intimacy-based sampling strategy. Subsequently, during the representation learning stage, node features under different meta-path views are generated and then aggregated to obtain the final exercise embeddings. The learned embeddings are optimized through three auxiliary tasks, anchored within a self-supervised learning paradigm. Extensive experiments across four public datasets demonstrate that our method can significantly enhance the predictive performance of downstream KT models.

Knowledge ontology enhanced model for explainable knowledge tracing

Knowledge Tracing (KT) aims to predict learners’ future learning outcomes based on their past learning interactions. Deep Knowledge Tracing (DKT) is a technology developed in recent years that employs deep learning techniques to dynamically track students’ learning progress and offer personalized learning support. Yet, existing research often miss the complex interplay between student characteristics and knowledge components, limiting interpretability and adaptability in assessments. Addressing this gap, we introduce the Ontology Perceptible Knowledge Tracing (OPKT) model, a novel approach that reconceptualizes student-knowledge interaction by integrating both student and knowledge ontologies directly into the tracing process. This integration allows for a more nuanced representation of learning interactions, significantly enhancing the predictive precision and interpretability of the model. The OPKT model extracts and utilizes ontology features—deriving student attributes from behavioral data and aligning them with knowledge aspects through sophisticated relationship mapping. This dual-layer integration captures the evolution of knowledge states more accurately, facilitating targeted educational interventions. The results of prediction on two publicly available datasets demonstrate that our proposed OPKT model achieves at least a 2% improvement in AUC, accurately assessing students’ learning outcomes and knowledge proficiency. Additionally, we conducted dimensionality reduction experiments and ablation studies to validate the interpretability of the model.

FDKT: Towards an Interpretable Deep Knowledge Tracing via Fuzzy Reasoning

In educational data mining, knowledge tracing (KT) aims to model learning performance based on student knowledge mastery. Deep-learning-based KT models perform remarkably better than traditional KT and have attracted considerable attention. However, most of them lack interpretability, making it challenging to explain why the model performed well in the prediction. In this paper, we propose an interpretable deep KT model, referred to as fuzzy deep knowledge tracing (FDKT) via fuzzy reasoning. Specifically, we formalize continuous scores into several fuzzy scores using the fuzzification module. Then, we input the fuzzy scores into the fuzzy reasoning module (FRM). FRM is designed to deduce the current cognitive ability, based on which the future performance was predicted. FDKT greatly enhanced the intrinsic interpretability of deep-learning-based KT through the interpretation of the deduction of student cognition. Furthermore, it broadened the application of KT to continuous scores. Improved performance with regard to both the advantages of FDKT was demonstrated through comparisons with the state-of-the-art models.

Psychological factors enhanced heterogeneous learning interactive graph knowledge tracing for understanding the learning process.

With the rapid expansion of online education, there is a burgeoning interest within the EdTech space to offer tailored learning experiences that cater to individual student's abilities and needs. Within this framework, knowledge tracing tasks have garnered considerable attention. The primary objective of knowledge tracing is to develop a model that assesses a student's proficiency in a particular skill based on their historical performance in exercises, enabling predictions regarding the likelihood of correct responses in future exercises. While existing knowledge tracing models often incorporate information such as students' exercise answering history and skill mastery level, they frequently overlook the students' mental states during the learning process. This paper addresses this gap by introducing a novel psychological factors-enhanced heterogeneous learning interactive graph knowledge tracing model (Psy-KT). This model delineates the interactions among students, exercises, and skills through a heterogeneous graph, supplementing it with four psychological factors that capture students' mental states during the learning process: frustration level, confusion level, concentration level, and boredom level. In the modeling of students' learning processes, we incorporate the forgetting curve and construct relevant cognitive parameters from the features. Additionally, we employ the Item Response Theory (IRT) model to predict students' performance in answering exercises at the subsequent time step. This model not only delves into the psychological aspects of students during the learning process but also integrates the simulation of forgetting, a natural phenomenon in the learning journey. The inclusion of cognitive parameters enhances the description of changes in students' abilities throughout the learning process. This dual focus allows for a more comprehensive understanding of students' learning behaviors while providing a high level of interpretability for the model. Empirical validation of the Psy-KT model is conducted using four publicly available datasets, demonstrating its superior performance in predicting students' future performance. Through rigorous experimentation, the integration of psychological and forgetting factors in the Psy-KT model not only improves predictive accuracy but also enables educators to offer more targeted tutoring and advice, enhancing the overall efficacy of the learning experience.

Integrating Models in Education: Evaluating Strategies and Enhancing Student Learning Through Advanced Analytical Methods

This paper undertakes an in-depth examination of contemporary educational models, focusing on their impact on student learning and teaching strategies. It contrasts static models like the Item Response Theory (IRT) with dynamic models, notably Knowledge Tracing (KT) and its extensions such as the Knowledge Tracing Model (KTM) with a "Tutor Intervention" element. These dynamic models, particularly the dynamic Bayesian network (DBN) structure of KT, provide a detailed perspective on student learning, accommodating temporal skill variations and diverse educational interventions. The study further explores learning decomposition, revealing its effectiveness in evaluating various reading practices and their influence on reading fluency, underscoring the need for personalized educational approaches. Additionally, the paper discusses the Bayesian Evaluation and Assessment framework within Intelligent Tutoring Systems (ITS), offering a holistic view of both the immediate and long-term effects of tutoring. Key insights are presented on the efficacy of different educational models in reading education, advocating for diversified reading practices and personalized learning strategies. The paper also identifies limitations in current models, such as high standard errors in learning decomposition and weak fits in models like LR-DBN, and proposes future research directions, including automated analysis and a hybrid approach combining human expertise with computational analysis. This approach aims to enhance educational data mining and inform effective educational strategies and outcomes.

ELAKT: Enhancing Locality for Attentive Knowledge Tracing

Knowledge tracing models based on deep learning can achieve impressive predictive performance by leveraging attention mechanisms. However, there still exist two challenges in attentive knowledge tracing (AKT): First, the mechanism of classical models of AKT demonstrates relatively low attention when processing exercise sequences with shifting knowledge concepts (KC), making it difficult to capture the comprehensive state of knowledge across sequences. Second, classical models do not consider stochastic behaviors, which negatively affects models of AKT in terms of capturing anomalous knowledge states. This article proposes a model of AKT, called Enhancing Locality for Attentive Knowledge Tracing (ELAKT), that is a variant of the deep KT model. The proposed model leverages the encoder module of the transformer to aggregate knowledge embedding generated by both exercises and responses over all timesteps. In addition, it uses causal convolutions to aggregate and smooth the states of local knowledge. The ELAKT model uses the states of comprehensive KCs to introduce a prediction correction module to forecast the future responses of students to deal with noise caused by stochastic behaviors. The results of experiments demonstrated that the ELAKT model consistently outperforms state-of-the-art baseline KT models.

Integrating learning factors and Bayesian network for interpretable knowledge tracing

Knowledge tracing aims to model learners’ knowledge mastery based on their historical interaction records and predict their future performance. Due to its great potential in enabling personalized learning in intelligent tutoring systems, it has received extensive attention. However, most deep learning-based knowledge tracing methods have significant predictive performance. It is difficult to extract meaningful interpretations from the thousands of parameters in neural networks. The interpretability of knowledge tracing refers to the ability of learners to easily understand the predicted results.To address this problem, based on learning factors that influence the learner’s exercise performance, this paper proposes a novel knowledge tracing model which is named Integrating Learning factors and Bayesian network for interpretable Knowledge Tracing (LBKT). Firstly, meaningful learning factors, including knowledge mastery, learning ability, and exercise difficulty, are calculated from learners’ historical interaction records using deep learning and statistical methods. Then, Bayesian network is constructed to capture the causal relation between the three learning factors and exercise response. Finally, the Bayesian network is generated through structure and parameter learning to obtain interpretable prediction of future exercise performance. The proposed model named LBKT is evaluated on three public real-world educational datasets. The experiment results demonstrate that our approach achieves better predictive performance compared to baseline knowledge tracing methods, while also exhibiting significant superiority in model interpretability.

An Enhanced Deep Knowledge Tracing Model via Multiband Attention and Quantized Question Embedding

An Enhanced Deep Knowledge Tracing Model via Multiband Attention and Quantized Question Embedding

Research on Knowledge Tracing-Based Classroom Network Characteristic Learning Engagement and Temporal-Spatial Feature Fusion

To accurately assess students’ cognitive state of knowledge points in the learning process within the smart classroom, a knowledge tracing (KT) model based on classroom network characteristic learning engagement and temporal-spatial feature fusion (CL-TSKT) is proposed. First, a classroom network is constructed based on the information of the student ID, seating relationship, student–student interaction, head-up or head-down state, and classroom network characteristics obtained from a smart classroom video. Second, a learning engagement model is established by utilizing the student–student interactions, head-up or head-down state, and classroom network characteristics. Finally, according to the learning engagement model and the knowledge point test data, a parallel temporal attention GRU network is proposed. It is utilized to extract the temporal features of the knowledge points and learning engagement. They are fused to obtain the knowledge point-learning engagement temporal characteristics and their associated attributes. Meanwhile, a CNN is used to extract the knowledge point-knowledge point spatial features. We consider the associative properties of knowledge point-knowledge points from a spatial perspective and fuse the knowledge point-knowledge point spatial features with the knowledge point-learning engagement temporal features. To accurately characterize the cognitive state of the knowledge points and provide effective support for teachers’ accurate and sustainable interventions for learners in the teaching and learning process, this paper conducts extensive experiments on four real datasets. The CL-TSKT model in this paper shows superior performance in all four evaluation metrics, compared with the state-of-the-art KT models.

Target hierarchy-guided knowledge tracing : Fine-grained knowledge state modeling

Knowledge Tracing (KT) focuses on modeling the exercise process of students, assessing their knowledge state changes during the exercise process, and further providing targeted guidance for teaching and learning. Current KT models have made significant progress by utilizing deep learning technologies to model relevant attributes of the questions. However, in current knowledge tracing strategies, we have yet to exhaustively explore how to precisely evaluate the hierarchies of students’ knowledge mastery to better discern their current target hierarchy. To address the limitations of the KT model in accurately identifying and positioning target hierarchy, our research focuses on two key areas: first, we dynamically track students’ target hierarchies by evaluating their feedback on questions at different hierarchies ; second, we assess their actual question-solving abilities within these target hierarchies, thereby optimizing our evaluation of their knowledge status. Based on these insights, we propose the Target Hierarchy-guided Knowledge Tracing (THKT) model. In this model, we first incorporate the identification of question hierarchy into the model representation. Then, to avoid homogenization of the target hierarchy, we dynamically track the appropriate hierarchy for students based on their varying feedback to questions of the same hierarchy, thereby pinpointing their learning target hierarchies. Simultaneously, we develop a KCs applied ability learning module that works in conjunction with the target hierarchies to generate interpretable prediction results. The proposed THKT model has been tested and evaluated using three public, real-world educational datasets. The findings clearly demonstrate that our approach shines in the realm of KT prediction tasks, providing significantly interpretability. For broader research, we plan to provide the source code at: https://github.com/xinjiesun-ustc/THKT to ensure accessibility and promote further innovation in this field.

A deeper knowledge tracking model integrating cognitive theory and learning behavior

Knowledge tracing (KT), which aims to trace human knowledge learning process by using machines, has widely applied in online learning systems. It dynamically models student’s knowledge states in relation to different learning factors through their learning interactions. Recently, KT has attracted many researches attention due to its good performance to using deep learning. Although most of KT models have shown outstanding results, they have limitations: either ignore the human cognitive law and learning behavior, or lack the ability to go deeper modeling to trace knowledge state. In this paper, we propose a deeper knowledge tracking model integrating cognitive theory and learning behavior (CLDKT). It united the advantages of memory network and recurrent neural network of the existing deep learning KT models for modeling student learning. To better implement CLDKT, we add the residual network (ResNet) to realize the deep modeling of learning behaviors. Extensive experiments on three open benchmark datasets to evaluate our model. Experimental results demonstrate that (I) CLDKT outperforms the state-of-the-art KT models on students’ performance prediction. (II) CLDKT can deeper modeling to trace knowledge state owing to the ResNet import. (III) CLDKT has better interpretability and predictability, which proves the effectiveness of the knowledge tracing model integrating cognitive law and learning behavior.