Deep knowledge tracing and engagement with MOOCs

Kritphong Mongkhonvanit; Klint Kanopka; David Lang

doi:10.1145/3303772.3303830

Deep knowledge tracing and engagement with MOOCs

Kritphong Mongkhonvanit, Klint Kanopka, David Lang

Applied Statistics, Social Science, and Humanities

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

MOOCs and online courses have notoriously high attrition [1]. One challenge is that it can be difficult to tell if students fail to complete because of disinterest or because of course difficulty. Utilizing a Deep Knowledge Tracing framework, we account for student engagement by including course interaction covariates. With these, we find that we can predict a student's next item response with over 88% accuracy. Using these predictions, targeted interventions can be offered to students and targeted improvements can be made to courses. In particular, this approach would allow for gating of content until a student has reasonable likelihood of succeeding.

Original language	English (US)
Title of host publication	Proceedings of the 9th International Conference on Learning Analytics and Knowledge
Subtitle of host publication	Learning Analytics to Promote Inclusion and Success, LAK 2019
Publisher	Association for Computing Machinery
Pages	340-342
Number of pages	3
ISBN (Electronic)	9781450362566
DOIs	https://doi.org/10.1145/3303772.3303830
State	Published - Mar 4 2019
Event	9th International Conference on Learning Analytics and Knowledge, LAK 2019 - Tempe, United States Duration: Mar 4 2019 → Mar 8 2019

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	9th International Conference on Learning Analytics and Knowledge, LAK 2019
Country/Territory	United States
City	Tempe
Period	3/4/19 → 3/8/19

Keywords

Item response
MOOCS
Neural networks
Video interactions

ASJC Scopus subject areas

Software
Human-Computer Interaction
Computer Vision and Pattern Recognition
Computer Networks and Communications

Access to Document

10.1145/3303772.3303830

Cite this

Mongkhonvanit, K., Kanopka, K., & Lang, D. (2019). Deep knowledge tracing and engagement with MOOCs. In Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019 (pp. 340-342). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3303772.3303830

Deep knowledge tracing and engagement with MOOCs. / Mongkhonvanit, Kritphong; Kanopka, Klint; Lang, David.
Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. Association for Computing Machinery, 2019. p. 340-342 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Mongkhonvanit, K, Kanopka, K & Lang, D 2019, Deep knowledge tracing and engagement with MOOCs. in Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 340-342, 9th International Conference on Learning Analytics and Knowledge, LAK 2019, Tempe, United States, 3/4/19. https://doi.org/10.1145/3303772.3303830

Mongkhonvanit K, Kanopka K, Lang D. Deep knowledge tracing and engagement with MOOCs. In Proceedings of the 9th International Conference on Learning Analytics and Knowledge: Learning Analytics to Promote Inclusion and Success, LAK 2019. Association for Computing Machinery. 2019. p. 340-342. (ACM International Conference Proceeding Series). doi: 10.1145/3303772.3303830

@inproceedings{0f38eff185bc463bb3be18b738c7de09,

title = "Deep knowledge tracing and engagement with MOOCs",

abstract = "MOOCs and online courses have notoriously high attrition [1]. One challenge is that it can be difficult to tell if students fail to complete because of disinterest or because of course difficulty. Utilizing a Deep Knowledge Tracing framework, we account for student engagement by including course interaction covariates. With these, we find that we can predict a student's next item response with over 88% accuracy. Using these predictions, targeted interventions can be offered to students and targeted improvements can be made to courses. In particular, this approach would allow for gating of content until a student has reasonable likelihood of succeeding.",

keywords = "Item response, MOOCS, Neural networks, Video interactions",

author = "Kritphong Mongkhonvanit and Klint Kanopka and David Lang",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 9th International Conference on Learning Analytics and Knowledge, LAK 2019 ; Conference date: 04-03-2019 Through 08-03-2019",

year = "2019",

month = mar,

day = "4",

doi = "10.1145/3303772.3303830",

language = "English (US)",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "340--342",

booktitle = "Proceedings of the 9th International Conference on Learning Analytics and Knowledge",

}

TY - GEN

T1 - Deep knowledge tracing and engagement with MOOCs

AU - Mongkhonvanit, Kritphong

AU - Kanopka, Klint

AU - Lang, David

PY - 2019/3/4

Y1 - 2019/3/4

N2 - MOOCs and online courses have notoriously high attrition [1]. One challenge is that it can be difficult to tell if students fail to complete because of disinterest or because of course difficulty. Utilizing a Deep Knowledge Tracing framework, we account for student engagement by including course interaction covariates. With these, we find that we can predict a student's next item response with over 88% accuracy. Using these predictions, targeted interventions can be offered to students and targeted improvements can be made to courses. In particular, this approach would allow for gating of content until a student has reasonable likelihood of succeeding.

AB - MOOCs and online courses have notoriously high attrition [1]. One challenge is that it can be difficult to tell if students fail to complete because of disinterest or because of course difficulty. Utilizing a Deep Knowledge Tracing framework, we account for student engagement by including course interaction covariates. With these, we find that we can predict a student's next item response with over 88% accuracy. Using these predictions, targeted interventions can be offered to students and targeted improvements can be made to courses. In particular, this approach would allow for gating of content until a student has reasonable likelihood of succeeding.

KW - Item response

KW - MOOCS

KW - Neural networks

KW - Video interactions

UR - http://www.scopus.com/inward/record.url?scp=85062794745&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062794745&partnerID=8YFLogxK

U2 - 10.1145/3303772.3303830

DO - 10.1145/3303772.3303830

M3 - Conference contribution

AN - SCOPUS:85062794745

T3 - ACM International Conference Proceeding Series

SP - 340

EP - 342

BT - Proceedings of the 9th International Conference on Learning Analytics and Knowledge

PB - Association for Computing Machinery

T2 - 9th International Conference on Learning Analytics and Knowledge, LAK 2019

Y2 - 4 March 2019 through 8 March 2019

ER -

Deep knowledge tracing and engagement with MOOCs

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this