Knowledge tracing: Modeling the acquisition of procedural knowledge

By Albert T. Corbett, John R. Anderson. User modeling and user-adapted interaction, 2005

2,472 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Science Applications

View Paper: https://www.semanticscholar.org/paper/645b2c28c28bd28eaa187a2faafa5ec12bc12e3a

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

In Computer Science Applications

Citations in the corpus

Individualized Bayesian Knowledge Tracing Models (2013, methodology): “[1], [5]), and [8]) describes quite different approaches to defining and learning student-specific parameters as well as report radically different performance measures.”
AutoTutor and affective autotutor: Learning by talking with cognitively and emotionally intelligent computers that talk back (2012, background): “Categories and Subject Descriptors: K.3.1 [Computers and Education]: Computer Uses in Education General Terms: Human Factors, Experimentation Additional Key Words and Phrases: Intelligent tutoring systems, affective computing, natural language understanding, user modeling, constructivism, deep…”
Performance Factors Analysis - A New Alternative to Knowledge Tracing (2009, background): “As a contrast, it helps to consider the knowledge tracing (KT) procedure pioneered by Atkinson[3] and developed by Corbett[1].”
Sample Efficient Policy Search for Optimal Stopping Domains (2017, methodology): “As is popular in the literature, we model student learning using the Bayesian Knowledge Tracing (BKT) model [Corbett and Anderson, 1995].”
Exploring the Assistance Dilemma in Experiments with Cognitive Tutors (2007, background): “learning method leads to improved learning (Anderson et al. 1989; Corbett and Anderson 1995).”
Towards an Appropriate Query, Key, and Value Computation for Knowledge Tracing (2020, background): “Traditional approaches to knowledge tracing include Bayesian knowledge tracing [3] and collaborative ﬁltering [20, 11].”
Context-Aware Attentive Knowledge Tracing (2020, methodology): “m in learner data analysis is to predict future learner performance (their responses to assessment questions), given their past performance, which is referred to as the knowledge tracing (KT) problem [3]. Over the last 30 years, numerous methods for solving the KT problem were developed based on two”
MathBERT: A Pre-trained Language Model for General NLP Tasks in Mathematics Education (2021, background): “Predicting the next question correctness as one of the KT tasks is well studied [4, 14, 15, 20, 31] but relies on high-dimensional sequential data.”
Detecting Student Misuse of Intelligent Tutoring Systems (2004, background): “Tutoring systems have become highly effective at assessing what skills a student possesses and tailoring the choice of exercises to a student’s skills [6,14], leading to curricula which are impressively effective in real-world classroom settings [7].”
New Potentials for Data-Driven Intelligent Tutoring System Development and Optimization (2013, methodology): “Corbett and Anderson (1995) did describe fitting individual weights to each of the Knowledge Tracing parameters, but this was done as a correction to the population parameters, rather than a direct parameter optimization for each student’s data. In contrast, recent work by Lee and Brunskill (2012) a”
Toward Meta-cognitive Tutoring: A Model of Help Seeking with a Cognitive Tutor (2006, methodology): “Cognitive Tutors keep track of a student’s knowledge growth over time by means of a Bayesian algorithm called knowledge tracing (Corbett & Anderson, 1995).”
Multi-Armed Bandits for Intelligent Tutoring Systems (2013, background): “Other services deliver directly the contents, e.g Nettutor, Smarthinking, and many software packages exist that facilitate the creation of pedagogical contents, e.g. Allivyonline, Capterra, E-lecta. knowledge level and particularities, as well as a personalized teaching strategy, has been identified”
Better to be frustrated than bored: The incidence, persistence, and impact of learners' cognitive-affective states during interactions with three different computer-based learning environments (2010, background): “, 1995; VanLehn, 1990) and promoting mastery learning through assessments of the probability that the student knows each skill relevant to the system (Corbett and Anderson, 1995).”
Empirical Evaluation of User Models and User-Adapted Systems (2001, background): “, 1997; Balabanovic̈, 1998), nine in student modeling (Nwana, 1991; London, 1992; Carbonaro et al., 1995; Corbett and Anderson, 1995; Kashihara et al., 1995; Shute, 1995; Webb and Kuzmycz, 1996; Mitrovic et al., 1996; Milne et al., 1996; Sison et al., 1998), nine in plan recognition/mixed-initiative”
Knowledge Tracing: A Survey (2022, methodology): “Early BKT models were primarily centered on the four parameters: prior learning parameter � (�0), learning rate parameter � (� ), guess parameter � (�), and slip parameter � (�) [25] and their student-speciic variants.”