Modeling Individualization in a Bayesian Networks Implementation of Knowledge Tracing

By Z. Pardos, Neil Heffernan III. User Modeling, Adaptation, and Personalization, 2010

403 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/3f7b79bbfad05383bb372403976d383062f03d56

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. Neil Heffernan III
3. Bernardo Pereira Nunes
4. Qing Wang
5. Ghodai M. Abdelrahman
6. Ryan Shaun Joazeiro de Baker
7. Xingjian Shi
8. Aritra Ghosh

In Computer Science Applications

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

Citations in the corpus

• The development of intuitive knowledge classifier and the modeling of domain dependent data (2013, background): “In last 10 years, the studies about user modeling as an independent research subject have become one step forward of ITS studies [18,22,23].”
• Knowledge Tracing: A Survey (2022, background): “Further work has been done through incorporating factors that relect the characteristics of individual students [28, 87], or the characteristics of speciic items of assessment within skills [88].”
• Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing (2020, neutral): “over time [3, 4, 23, 17, 15, 16, 21, 18, 9, 19].”
• 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.”
• Addressing two problems in deep knowledge tracing via prediction-consistent regularization (2018, background): “Extensive works have also been conducted to empower the individualization of BKT on both skill-specific parameters [9, 10] and studentspecific parameters [20].”
• Context-Aware Attentive Knowledge Tracing (2020, background): “The first class centered around the Bayesian knowledge tracing (BKT) method [19, 35] where knowledge ( h t ) is a binary-valued scalar that characterizes whether or not a learner masters the (single) concept covered by a question.”
• New Potentials for Data-Driven Intelligent Tutoring System Development and Optimization (2013, background): “Similarly, Pardos and Heffernan (2010) extended the Knowledge Tracing model to allow for different, student-specific initial probabilities of knowing the material.”
• Individualized Bayesian Knowledge Tracing Models (2013, methodology): “However, a large body of research strongly suggests that studentspecific variability in the data, when accounted for, could enhance model accuracy [5,6,8].”
• A review of recent advances in learner and skill modeling in intelligent learning environments (2012, methodology): “…such as the contextualization of estimates of guessing and slipping parameters (Baker et al. 2008a ), estimates of the probability of transition from use of help features (Beck et al. 2008), and estimates of the initial probability that the student knows the skill (Pardos and Heffernan 2010a).”