Predicting student grades from online, collaborative social learning metrics using K-NN

Matthew Yee-King; Andreu Grimalt-Reynes; Mark d’Inverno

Predicting student grades from online, collaborative social learning metrics using K-NN

Matthew Yee-King, Andreu Grimalt-Reynes, Mark d’Inverno

Academy of Music

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

We describe a collaborative video annotation system that aims to engage learners in a focused, collaborative process of content sharing and discussion, and explain how it was used in an online creative programming MOOC on Coursera. We explore the use of K-NN (K nearest neighbour) to predict which of a variable number of evenly spaced, final grade bands students will fall into based solely on a feature vector consisting of the total number of UI click and mouseover events they generated during the course. We were able to classify students into pass/fail bands with 88% precision; with 3 grade bands, precision was 77%, going down to 31% with 10 grade bands. Typically, a feature subset containing less than half of the available features provided the best performance.

Original language	English
Title of host publication	Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016
Editors	Tiffany Barnes, Min Chi, Mingyu Feng
Publisher	International Conference on Educational Data Mining
Pages	654-655
Number of pages	2
Publication status	Published - 29 Jun 2016
Event	9th International Conference on Educational Data Mining, EDM 2016 - Raleigh, United States Duration: 29 Jun 2016 → 2 Jul 2016 https://educationaldatamining.org/EDM2016/ https://www.educationaldatamining.org/EDM2016/proceedings/edm2016_proceedings.pdf

Publication series

Name	Proceedings of the International Conference on Educational Data Mining

Conference

Conference	9th International Conference on Educational Data Mining, EDM 2016
Country/Territory	United States
City	Raleigh
Period	29/06/16 → 2/07/16
Internet address	https://educationaldatamining.org/EDM2016/ https://www.educationaldatamining.org/EDM2016/proceedings/edm2016_proceedings.pdf

Access to Document

https://educationaldatamining.org/EDM2016/proceedings/paper_120.pdf

Cite this

Yee-King, M., Grimalt-Reynes, A., & d’Inverno, M. (2016). Predicting student grades from online, collaborative social learning metrics using K-NN. In T. Barnes, M. Chi, & M. Feng (Eds.), Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016 (pp. 654-655). (Proceedings of the International Conference on Educational Data Mining). International Conference on Educational Data Mining. https://educationaldatamining.org/EDM2016/proceedings/paper_120.pdf

Yee-King, Matthew ; Grimalt-Reynes, Andreu ; d’Inverno, Mark. / Predicting student grades from online, collaborative social learning metrics using K-NN. Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016. editor / Tiffany Barnes ; Min Chi ; Mingyu Feng. International Conference on Educational Data Mining, 2016. pp. 654-655 (Proceedings of the International Conference on Educational Data Mining).

@inproceedings{f9d0ff5f33414155821436e5f21507bb,

title = "Predicting student grades from online, collaborative social learning metrics using K-NN",

abstract = "We describe a collaborative video annotation system that aims to engage learners in a focused, collaborative process of content sharing and discussion, and explain how it was used in an online creative programming MOOC on Coursera. We explore the use of K-NN (K nearest neighbour) to predict which of a variable number of evenly spaced, final grade bands students will fall into based solely on a feature vector consisting of the total number of UI click and mouseover events they generated during the course. We were able to classify students into pass/fail bands with 88% precision; with 3 grade bands, precision was 77%, going down to 31% with 10 grade bands. Typically, a feature subset containing less than half of the available features provided the best performance.",

author = "Matthew Yee-King and Andreu Grimalt-Reynes and Mark d{\textquoteright}Inverno",

note = "Publisher Copyright: {\textcopyright} 2016 International Educational Data Mining Society. All rights reserved.; 9th International Conference on Educational Data Mining, EDM 2016 ; Conference date: 29-06-2016 Through 02-07-2016",

year = "2016",

month = jun,

day = "29",

language = "English",

series = "Proceedings of the International Conference on Educational Data Mining",

publisher = "International Conference on Educational Data Mining",

pages = "654--655",

editor = "Tiffany Barnes and Min Chi and Mingyu Feng",

booktitle = "Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016",

url = "https://educationaldatamining.org/EDM2016/, https://www.educationaldatamining.org/EDM2016/proceedings/edm2016_proceedings.pdf",

}

Yee-King, M, Grimalt-Reynes, A & d’Inverno, M 2016, Predicting student grades from online, collaborative social learning metrics using K-NN. in T Barnes, M Chi & M Feng (eds), Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016. Proceedings of the International Conference on Educational Data Mining, International Conference on Educational Data Mining, pp. 654-655, 9th International Conference on Educational Data Mining, EDM 2016, Raleigh, United States, 29/06/16. <https://educationaldatamining.org/EDM2016/proceedings/paper_120.pdf>

Predicting student grades from online, collaborative social learning metrics using K-NN. / Yee-King, Matthew; Grimalt-Reynes, Andreu; d’Inverno, Mark.
Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016. ed. / Tiffany Barnes; Min Chi; Mingyu Feng. International Conference on Educational Data Mining, 2016. p. 654-655 (Proceedings of the International Conference on Educational Data Mining).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - Predicting student grades from online, collaborative social learning metrics using K-NN

AU - Yee-King, Matthew

AU - Grimalt-Reynes, Andreu

AU - d’Inverno, Mark

PY - 2016/6/29

Y1 - 2016/6/29

N2 - We describe a collaborative video annotation system that aims to engage learners in a focused, collaborative process of content sharing and discussion, and explain how it was used in an online creative programming MOOC on Coursera. We explore the use of K-NN (K nearest neighbour) to predict which of a variable number of evenly spaced, final grade bands students will fall into based solely on a feature vector consisting of the total number of UI click and mouseover events they generated during the course. We were able to classify students into pass/fail bands with 88% precision; with 3 grade bands, precision was 77%, going down to 31% with 10 grade bands. Typically, a feature subset containing less than half of the available features provided the best performance.

AB - We describe a collaborative video annotation system that aims to engage learners in a focused, collaborative process of content sharing and discussion, and explain how it was used in an online creative programming MOOC on Coursera. We explore the use of K-NN (K nearest neighbour) to predict which of a variable number of evenly spaced, final grade bands students will fall into based solely on a feature vector consisting of the total number of UI click and mouseover events they generated during the course. We were able to classify students into pass/fail bands with 88% precision; with 3 grade bands, precision was 77%, going down to 31% with 10 grade bands. Typically, a feature subset containing less than half of the available features provided the best performance.

UR - https://www.educationaldatamining.org/EDM2016/proceedings/edm2016_proceedings.pdf

UR - http://www.scopus.com/inward/record.url?scp=85050874107&partnerID=8YFLogxK

M3 - Conference proceeding

AN - SCOPUS:85050874107

T3 - Proceedings of the International Conference on Educational Data Mining

SP - 654

EP - 655

BT - Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016

A2 - Barnes, Tiffany

A2 - Chi, Min

A2 - Feng, Mingyu

PB - International Conference on Educational Data Mining

T2 - 9th International Conference on Educational Data Mining, EDM 2016

Y2 - 29 June 2016 through 2 July 2016

ER -

Yee-King M, Grimalt-Reynes A, d’Inverno M. Predicting student grades from online, collaborative social learning metrics using K-NN. In Barnes T, Chi M, Feng M, editors, Proceedings of the 9th International Conference on Educational Data Mining, EDM 2016. International Conference on Educational Data Mining. 2016. p. 654-655. (Proceedings of the International Conference on Educational Data Mining).

Predicting student grades from online, collaborative social learning metrics using K-NN

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this