CMKT: Concept Map Driven Knowledge Tracing

Lu, Yu; Chen, Penghe; Pian, Yang; Zheng, Vincent W.

doi:10.1109/tlt.2022.3196355

Cited by 21 publications

(6 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These traditional approaches primarily rely on learners' answered exercises and their correctness, disregarding the abundance of interactive information present in real-world learning scenarios. Factors such as knowledge point difficulty [26], exercise text [42], learner ability [3], response duration time [43], and knowledge associations [44] are often overlooked. As a result, scholars have endeavored to integrate additional edge features into the traditional deep knowledge tracing model to enhance its effectiveness [26,[45][46][47].…”

Section: Multi-feature Analysis In Knowledge Tracingmentioning

confidence: 99%

Multiple Learning Features–Enhanced Knowledge Tracing Based on Learner–Resource Response Channels

et al. 2023

View full text Add to dashboard Cite

Knowledge tracing is a crucial task that involves modeling learners’ knowledge levels and predicting their future learning performance. However, traditional deep knowledge tracing approaches often overlook the intrinsic relationships among learning features, treating them equally and failing to align with real learning scenarios. To address these issues, this paper proposes the multiple learning features, enhanced knowledge tracing (MLFKT) framework. Firstly, we construct learner–resource response (LRR) channels based on psychometric theory, establishing stronger intrinsic connections among learning features and overcoming the limitations of the item response theory. Secondly, we leverage stacked auto-encoders to extract low-dimensional embeddings for different LRR channels with denser representations. Thirdly, considering the varying impact of different LRR channels on learning performance, we introduce an attention mechanism to assign distinct weights to each channel. Finally, to address the challenges of memory retention and forgetting in the learning process and to handle long-term dependency issues, we employ a bidirectional long short-term memory network to model learners’ knowledge states, enabling accurate prediction of learning performance. Through extensive experiments on two real datasets, we demonstrate the effectiveness of our proposed MLFKT approach, which outperforms six traditional methods. The newly proposed method can enhance educational sustainability by improving the diagnosis of learners’ self-cognitive structures and by empowering teachers to intervene and personalize their teaching accordingly.

show abstract

Section: Multi-feature Analysis In Knowledge Tracingmentioning

confidence: 99%

Multiple Learning Features–Enhanced Knowledge Tracing Based on Learner–Resource Response Channels

et al. 2023

View full text Add to dashboard Cite

show abstract

“…This metaheuristic model was developed using a genetic algorithm (GA) and ant colony optimization (ACO) algorithm. Lu et al [18] proposed a model to trace students' knowledge status using a recurrent neural network (RNN) [19] that exploits the relationship and topology information among KCs.…”

Section: Related Work a Finding Relationsmentioning

confidence: 99%

Optimal Knowledge Component Extracting Model for Knowledge-Concept Graph Completion in Education

Choi¹,

Lee

2023

IEEE Access

View full text Add to dashboard Cite

As people have become accustomed to non-face-to-face education because of the COVID-19 pandemic, adaptive and personalized learning is being emphasized in the field of education. Learning paths suitable for each student may differ from those normally provided by teachers. To support coaching based on the concept of adaptive learning, the first step is to discover the relationships among the concepts in the curriculum provided in the form of a knowledge graph. In this study, feature reduction for the target knowledge-concept was first performed using Elastic Net and Random Forest algorithms, which are known to have the best performance in machine learning. Deep knowledge tracing (DKT) in the form of a dual-net, which is more efficient because of the already slimmer data, was then applied to increase the accuracy of feature selection. The new approach, termed the optimal knowledge component extracting (OKCE) model, was proven to be superior to a feature reduction approach using only Elastic Net and Random Forest using both open and commercial datasets. Finally, the OKCE model showed a meaningful knowledge-concept graph that could help teachers in adaptive and personalized learning. INDEX TERMSDeep learning based knowledge tracing (DKT), dual-net, elastic net, feature selection, knowledge component (KC), least absolute shrinkage and selection operator (LASSO), random forest (RF).

show abstract

“…The main AI used in this system is the knowledge-based recommendation approach, which collects and analyzes the data (including both knowledge structure and cognitive state) to generate the adaptive leaning cognitive map and then make personalized learning recommendations (e.g., learning materials) accordingly [14]. The student knowledge status can be estimated using deep learning techniques in an accurate and explainable way [16][17][18]. Specifically, the deep learning-based knowledge tracing models can be used, which utilize the trained recurrent neural networks to estimate whether the individual student mastered the fine-grained concepts.…”

Section: Theoretical Framework Of the Studymentioning

confidence: 99%

Teachers’ and Students’ Views of Using an AI-Aided Educational Platform for Supporting Teaching and Learning at Chinese Schools

et al. 2022

Self Cite

View full text Add to dashboard Cite

In Chinese schools in less advanced places, there is an urgent need to improve the quality of education and educational equity. This study aims to investigate how an AI-aided educational platform can be used to provide additional teaching and learning resources to serve this need. The AI-aided educational platform used in this study is called Smart-Learning Partner (SLP), which is based on AI technology to provide new opportunities for personalized learning and more educational resources. A qualitative research method was applied in this study. We interviewed and surveyed 98 students and 32 teachers at 9 Chinese schools located in less developed areas. We used content analysis to interpret the findings based on students’ and teachers’ experiences of using the SLP platform. The data demonstrated that this kind of AI-aided educational platform was viewed by students and teachers as a useful tool in students’ learning and teachers’ work. It provided additional possibilities to students and teachers with its rich assessment tools, personalized and overall student learning analysis reports, plentiful high-quality mini-lecture videos, and recommendations from the platform based on the students’ needs for further enhancement study. However, challenges still exist. Adequate electronic devices for students are needed, especially in schools in less developed areas. Students and teachers called for user-friendly interfaces and features, social interaction aspects, and gamification mechanisms with recent online learning platforms. We conclude that based on the teachers’ and students’ views, AI-aided education platforms are useful tools for supporting teaching and learning in Chinese school.

show abstract

CMKT: Concept Map Driven Knowledge Tracing

Cited by 21 publications

References 61 publications

Multiple Learning Features–Enhanced Knowledge Tracing Based on Learner–Resource Response Channels

Multiple Learning Features–Enhanced Knowledge Tracing Based on Learner–Resource Response Channels

Optimal Knowledge Component Extracting Model for Knowledge-Concept Graph Completion in Education

Teachers’ and Students’ Views of Using an AI-Aided Educational Platform for Supporting Teaching and Learning at Chinese Schools

Contact Info

Product

Resources

About