Individualized Bayesian Knowledge Tracing Models

By Michael V. Yudelson, K. Koedinger, Geoffrey J. Gordon. International Conference on Artificial Intelligence in Education, 2013

523 citations recorded by the source corpus.

Bayesian Knowledge Tracing (BKT)[1] is a user modeling method extensively used in the area of Intelligent Tutoring Systems. In the standard BKT implementation, there are only skill-specific parameters. However, a large body of research strongly suggests that student-specific variability in the data, when accounted for, could enhance model accuracy [5,6,8]. In this work, we revisit the problem of introducing student-specific parameters into BKT on a larger scale. We show that student-specific parameters lead to a tangible improvement when predicting the data of unseen students, and that parameterizing students’ speed of learning is more beneficial than parameterizing a priori knowledge.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/55a51b86f6739f1d04556ffe0b69ae2d77a347b3

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

1. Dit-Yan Yeung
2. Surya Ganguli
3. Neil Heffernan III
4. Jascha Narain Sohl-Dickstein
5. Irwin King
6. Bernardo Pereira Nunes
7. Qing Wang
8. Ghodai M. Abdelrahman

In Computer Science Applications

1. Neil Heffernan III
2. Dit-Yan Yeung
3. Bernardo Pereira Nunes
4. Qing Wang
5. Ghodai M. Abdelrahman
6. Chun-Kit Yeung
7. Andrew S. Lan
8. Aritra Ghosh

Citations in the corpus

• Dynamic Key-Value Memory Networks for Knowledge Tracing (2016, background): “Many following variations were raised by integrating personalization study [19, 33], exercise diversity [20], and other information [4, 23] into the Bayesian framework.”
• Deep Knowledge Tracing (2015, methodology): “Recent extensions to this model include contextualization of guessing and slipping estimates [7], estimating prior knowledge for individual learners [33], and estimating problem difficulty [23].”
• 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…”
• EKT: Exercise-Aware Knowledge Tracing for Student Performance Prediction (2019, background): “, exercise difficulty [25], multiple knowledge concepts [26] and student individuals [27].”
• Knowledge Tracing: A Survey (2022, methodology): “Parameter [24] [83] [62] [123] [56] skill student skill student skill student skill student skill student”
• Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing (2020, background): “ude Bayesian Knowledge Tracing (BKT) [3], Collaborative Filtering (CF) [20,11] and many others. BKT is a classical, prominent approach to knowledge tracing that has been studied extensively over time [3,4,23,17,15,16,21,18,9,19]. BKT represents a student’s knowledge state as a tuple of binary values”
• Addressing two problems in deep knowledge tracing via prediction-consistent regularization (2018, background): “[4] and skill dependency [5] have been proposed. Extensive works have also been conducted to empower the individualization of BKT on both skill-specific parameters [9,10] and studentspecific parameters [20]. Some other attempts have been made to extend the capabilities of BKT on the partial score [17]”