Learning Factors Analysis - A General Method for Cognitive Model Evaluation and Improvement

By Hao Cen, K. Koedinger, Brian W. Junker. International Conference on Intelligent Tutoring Systems, 2006

631 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/02f63887e71f885e6c47313083cf729589e46b6d

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 Experimental and Cognitive Psychology

Citations in the corpus

Item Response Theory—A Statistical Framework for Educational and Psychological Measurement (2021, neutral): “In particular, such models have played an important role in intelligent tutoring systems (Cen et al., 2006; Doignon and Falmagne, 2012) to support personalized learning.”
Knowledge Tracing: A Survey (2022, methodology): “• Additive Factor Model (AFM) The Additive Factor Model [17], originated from Learning Factors Analysis (LFA) [16], is a logistic regression model under four assumptions: (1) the prior knowledge of students may vary; (2) students learn at the same rate; (3) some skills are more likely to be known th”
A review of recent advances in learner and skill modeling in intelligent learning environments (2012, methodology): “(Cen et al. 2006; Pavlik et al. 2009a) are alternative approaches to BKT for inferring changes in knowledge from sequential data that may offer advantages over BKT (see also Yudelson et al.”
Multi-Armed Bandits for Intelligent Tutoring Systems (2013, methodology): “Several cognitive models have been proposed to describe the learning process of the students: HMM models to perform the KT [22], recent results also include methods to simultaneously discover the relation between activities and KC [30] and Additive factor models [18] and its more advanced variants [”
New Potentials for Data-Driven Intelligent Tutoring System Development and Optimization (2013, background): “More recently, Chi et al. (2011) modeled physics tutoring as a Markov Decision Process (MDP) to inform which type of activity to provide at certain junctures: whether to elicit student performance of a step (to practice the underlying skill) or tell the student how to perform the step (as an example”
A Data Repository for the EDM Community: The PSLC DataShop (2010, methodology): “The dashed curve represents the predicted curve values, based on the Learning Factor Analysis (LFA) model [14], a variant of Item Response Theory.”
Performance Factors Analysis - A New Alternative to Knowledge Tracing (2009, methodology): “For example, as part of a search algorithm this model has been used to split knowledge components along multiple factors to determine the KC to item assignment (also known as the Q matrix) that represents the data best while still controlling for model complexity [2].”
Addressing two problems in deep knowledge tracing via prediction-consistent regularization (2018, methodology): “In the 2000s, learning factors analysis (LFA) [1] was proposed to model student knowledge states using the logistic regression model to deal with the multi-KCs issue and to incorporate student ability into the model.”
Context-Aware Attentive Knowledge Tracing (2020, methodology): “Other methods, e.g., additive factor models [1], performance factor analysis [22], the difficulty, ability, and student history (DASH) model [15], and a few recent methods including knowledge factorization machines [30] and an extension to the DASH model, the DAS3H model [2], used hand-crafted…”