Ability boosted knowledge tracing

Liu, Sanya; Yu, Jianyong; Li, Qing; Liang, Ruxia; Zhang, Yunhan; Shen, Xiaoxuan; Sun, Jianwen

doi:10.1016/j.ins.2022.02.044

Cited by 25 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It introduced the ability factor into the attribution of feedback, and designed a continuous matrix factorization model. The results proved that the proposed method was better than other KT algorithms in terms of quantitatively evaluated predictive accuracy [15]. This study innovatively introduced the influence of mental ability factors to optimize the KT system more comprehensively.…”

Section: Related Workmentioning

confidence: 75%

See 1 more Smart Citation

Traditional Cultural Network Online Education Integrating Deep Learning and Knowledge Tracking

Zhao,

Sun

2024

SCPE

View full text Add to dashboard Cite

With the popularization of the computer network and the development of artificial intelligence technology, the traditional education industry has been reformed. In the past two years, online education has developed rapidly. The combination of the Internet and education enables students to study online at any time, no longer relying on the time and place requirements in traditional education. However, with the rapid development of online education, many problems have gradually emerged. In online education, with a large amount of knowledge and question banks, students are faced with a large number of choices. Therefore, positioning and tracking the knowledge level of students and realizing personalized online education have become the main problems facing the moment. Based on this, this study integrates deep learning and knowledge tracking technology to build a traditional cultural network online education model, aiming at accurately positioning students’ knowledge levels and recommending personalized question banks. The experimental results show that the average AUC of the model proposed in this study is 0.781, and the average accuracy rate is 0.886, which is significantly better than other online education models. Through the combination of deep learning and knowledge tracking technology, the research successfully provides a new and efficient model for personalized learning in the field of online education, which is of great guiding value for promoting further innovation and development of online education. In addition, the research also provides practical solution strategies for related fields, which have obvious practical significance and popularization value.

show abstract

Section: Related Workmentioning

confidence: 75%

“…The user representation is obtained according to the probability, and the calculation process is shown in equation 3. 15.…”

Section: Construction Of Kt Online Education Model Based On DLmentioning

confidence: 99%

Traditional Cultural Network Online Education Integrating Deep Learning and Knowledge Tracking

Zhao,

Sun

2024

SCPE

View full text Add to dashboard Cite

show abstract

“…DKVMN has expanded the new research direction of knowledge tracing by better capturing the dependency relationships between knowledge points and by addressing the issue of accurately tracking learners' mastery of specific knowledge points [31]. However, the utilization of deep learning in knowledge tracing is not limited to DKVMN, as more and more deep learning algorithms are being applied to various methodological aspects of knowledge tracing to better extract and represent the entire learning process of learners [32][33][34]. For instance, Wang et al proposed a learnerpersonalized modeling approach based on convolutional neural networks (CNN) [35] for knowledge tracing tasks [36].…”

Section: Deep-learning-based 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

“…[59], [41], [ [20], [74], [34], [36], [75], [37], [38], [39], [76] [27], [43], [44], [52], [45], [68], [54], [37], [47], [46] [69], [55], [56], [57], [58], [59], [60], [61], [62], [50] [34], [63], [59] [20], [42], [77], [79] Hypothesis set [71], [33], [38], [78], [47], [49] [53], [72], [51] [71], [26], [48], [33], [49], [40] [48], [13], [70], [41], [64],…”

Section: Domain Knowledgementioning

confidence: 99%

Hybrid Models for Knowledge Tracing: a Systematic Literature Review

Zanellati¹,

Mitri²,

Gabbrielli³

et al. 2023

Preprint

View full text Add to dashboard Cite

<p>Knowledge Tracing is a well-known problem often tackled through purely data-driven approaches. In recent years, many advances have been made in research with various machine learning and deep learning techniques. Despite their satisfactory performance, they have some pitfalls, e.g. modeling one skill at a time, ignoring the relationships between different skills, or inconsistency for the predictions, i.e. sudden spikes and falls across time steps. For this reason, hybrid machine-learning techniques have also been explored. With this systematic literature review, we aim to illustrate this field's state of the art. Specifically, we want to identify the potential and the frontiers in integrating prior knowledge sources in the traditional machine learning pipeline as a supplement to the normally considered data. We applied a qualitative analysis to distill a taxonomy with three dimensions: knowledge source, knowledge representation, and knowledge integration. Exploiting this taxonomy, we also conducted a quantitative analysis to detect the most common approaches.</p>

show abstract

Ability boosted knowledge tracing

Cited by 25 publications

References 18 publications

Traditional Cultural Network Online Education Integrating Deep Learning and Knowledge Tracking

Traditional Cultural Network Online Education Integrating Deep Learning and Knowledge Tracking

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

Hybrid Models for Knowledge Tracing: a Systematic Literature Review

Contact Info

Product

Resources

About