Knowledge tracing using the brain

David Halpern, Shannon Tubridy, Hong Yu Wang, Camille Gasser, Pamela Osborn Popp, Lila Davachi, Todd Gureckis

Research output: Contribution to conferencePaper

Abstract

Knowledge tracing is a popular and successful approach to modeling student learning. In this paper we investigate whether the addition of neuroimaging observations to a knowledge tracing model enables accurate prediction of memory performance in held-out data. We propose a Hidden Markov Model of memory acquisition related to Bayesian Knowledge Tracing and show how continuous functional magnetic resonance imaging (fMRI) signals can be incorporated as observations related to latent knowledge states. We then show, using data collected from a simple second-language learning experiment, that fMRI data acquired during a learning session can be used to improve predictions about student memory at test. The fitted models can also potentially give new insight into the neural mechanisms that contribute to learning and memory.

Original languageEnglish (US)
StatePublished - Jan 1 2018
Event11th International Conference on Educational Data Mining, EDM 2018 - Buffalo, United States
Duration: Jul 15 2018Jul 18 2018

Conference

Conference11th International Conference on Educational Data Mining, EDM 2018
CountryUnited States
CityBuffalo
Period7/15/187/18/18

Fingerprint

Brain
Data storage equipment
Students
Neuroimaging
Hidden Markov models
Experiments
Magnetic Resonance Imaging

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems

Cite this

Halpern, D., Tubridy, S., Wang, H. Y., Gasser, C., Popp, P. O., Davachi, L., & Gureckis, T. (2018). Knowledge tracing using the brain. Paper presented at 11th International Conference on Educational Data Mining, EDM 2018, Buffalo, United States.

Knowledge tracing using the brain. / Halpern, David; Tubridy, Shannon; Wang, Hong Yu; Gasser, Camille; Popp, Pamela Osborn; Davachi, Lila; Gureckis, Todd.

2018. Paper presented at 11th International Conference on Educational Data Mining, EDM 2018, Buffalo, United States.

Research output: Contribution to conferencePaper

Halpern, D, Tubridy, S, Wang, HY, Gasser, C, Popp, PO, Davachi, L & Gureckis, T 2018, 'Knowledge tracing using the brain' Paper presented at 11th International Conference on Educational Data Mining, EDM 2018, Buffalo, United States, 7/15/18 - 7/18/18, .
Halpern D, Tubridy S, Wang HY, Gasser C, Popp PO, Davachi L et al. Knowledge tracing using the brain. 2018. Paper presented at 11th International Conference on Educational Data Mining, EDM 2018, Buffalo, United States.
Halpern, David ; Tubridy, Shannon ; Wang, Hong Yu ; Gasser, Camille ; Popp, Pamela Osborn ; Davachi, Lila ; Gureckis, Todd. / Knowledge tracing using the brain. Paper presented at 11th International Conference on Educational Data Mining, EDM 2018, Buffalo, United States.
@conference{8718d87174464b9fb936b0b798bda74b,
title = "Knowledge tracing using the brain",
abstract = "Knowledge tracing is a popular and successful approach to modeling student learning. In this paper we investigate whether the addition of neuroimaging observations to a knowledge tracing model enables accurate prediction of memory performance in held-out data. We propose a Hidden Markov Model of memory acquisition related to Bayesian Knowledge Tracing and show how continuous functional magnetic resonance imaging (fMRI) signals can be incorporated as observations related to latent knowledge states. We then show, using data collected from a simple second-language learning experiment, that fMRI data acquired during a learning session can be used to improve predictions about student memory at test. The fitted models can also potentially give new insight into the neural mechanisms that contribute to learning and memory.",
author = "David Halpern and Shannon Tubridy and Wang, {Hong Yu} and Camille Gasser and Popp, {Pamela Osborn} and Lila Davachi and Todd Gureckis",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
note = "11th International Conference on Educational Data Mining, EDM 2018 ; Conference date: 15-07-2018 Through 18-07-2018",

}

TY - CONF

T1 - Knowledge tracing using the brain

AU - Halpern, David

AU - Tubridy, Shannon

AU - Wang, Hong Yu

AU - Gasser, Camille

AU - Popp, Pamela Osborn

AU - Davachi, Lila

AU - Gureckis, Todd

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Knowledge tracing is a popular and successful approach to modeling student learning. In this paper we investigate whether the addition of neuroimaging observations to a knowledge tracing model enables accurate prediction of memory performance in held-out data. We propose a Hidden Markov Model of memory acquisition related to Bayesian Knowledge Tracing and show how continuous functional magnetic resonance imaging (fMRI) signals can be incorporated as observations related to latent knowledge states. We then show, using data collected from a simple second-language learning experiment, that fMRI data acquired during a learning session can be used to improve predictions about student memory at test. The fitted models can also potentially give new insight into the neural mechanisms that contribute to learning and memory.

AB - Knowledge tracing is a popular and successful approach to modeling student learning. In this paper we investigate whether the addition of neuroimaging observations to a knowledge tracing model enables accurate prediction of memory performance in held-out data. We propose a Hidden Markov Model of memory acquisition related to Bayesian Knowledge Tracing and show how continuous functional magnetic resonance imaging (fMRI) signals can be incorporated as observations related to latent knowledge states. We then show, using data collected from a simple second-language learning experiment, that fMRI data acquired during a learning session can be used to improve predictions about student memory at test. The fitted models can also potentially give new insight into the neural mechanisms that contribute to learning and memory.

UR - http://www.scopus.com/inward/record.url?scp=85064806712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064806712&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:85064806712

ER -