Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study

Soude Fazeli; Enayat Rajabi; Leonardo Lezcano; Hendrik Drachsler; Peter Sloep

doi:10.1109/icalt.2016.119

Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study

Soude Fazeli, Enayat Rajabi, Leonardo Lezcano, Hendrik Drachsler, Peter Sloep

Multimedia Computing

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

Almost all studies on course recommenders in online platforms target closed online platforms that belong to a University or other provider. Recently, a demand has developed that targets open platforms. Such platforms lack rich user profiles with content metadata. Instead they log user interactions. We report on how user interactions and activities tracked in open online learning platforms may generate recommendations. We use data from the OpenU open online learning platform in use by the Open University of the Netherlands to investigate the application of several state-of-the-art recommender algorithms, including a graph-based recommender approach. It appears that user-based and memory-based methods perform better than model-based and factorization methods. Particularly, the graph-based recommender system outperforms the classical approaches on prediction accuracy of recommendations in terms of recall.

Original language	English
Title of host publication	2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT)
Editors	J.M. Spector, C.C. Tsai, D.M. Sampson, Kinshuk, R. Huang, N.S. Chen, P. Resta
Place of Publication	Piscataway
Publisher	IEEE
Pages	423-427
Number of pages	5
ISBN (Electronic)	978-1-4673-9041-5
ISBN (Print)	978-1-4673-9042-2
DOIs	https://doi.org/10.1109/icalt.2016.119
Publication status	Published - 1 Dec 2016
Event	2016 IEEE 16th International Conference on Advanced Learning Technologies - Austin, TX, United States Duration: 25 Jul 2016 → 28 Jul 2016 http://www.ask4research.info/icalt/2016/

Conference

Conference	2016 IEEE 16th International Conference on Advanced Learning Technologies
Abbreviated title	ICALT
Country/Territory	United States
City	Austin, TX
Period	25/07/16 → 28/07/16
Internet address	http://www.ask4research.info/icalt/2016/

Keywords

recommender systems
collabortive filtering
open online course
performance
accuracy
matrix factorization

Access to Document

10.1109/icalt.2016.119

Cite this

Fazeli, S., Rajabi, E., Lezcano, L., Drachsler, H., & Sloep, P. (2016). Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study. In J. M. Spector, C. C. Tsai, D. M. Sampson, Kinshuk, R. Huang, N. S. Chen, & P. Resta (Eds.), 2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT) (pp. 423-427). IEEE. https://doi.org/10.1109/icalt.2016.119

@inproceedings{000b6fae5e6d4da6bd83591273ed76e5,

title = "Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study",

abstract = "Almost all studies on course recommenders in online platforms target closed online platforms that belong to a University or other provider. Recently, a demand has developed that targets open platforms. Such platforms lack rich user profiles with content metadata. Instead they log user interactions. We report on how user interactions and activities tracked in open online learning platforms may generate recommendations. We use data from the OpenU open online learning platform in use by the Open University of the Netherlands to investigate the application of several state-of-the-art recommender algorithms, including a graph-based recommender approach. It appears that user-based and memory-based methods perform better than model-based and factorization methods. Particularly, the graph-based recommender system outperforms the classical approaches on prediction accuracy of recommendations in terms of recall.",

keywords = "recommender systems, collabortive filtering, open online course, performance, accuracy, matrix factorization",

author = "Soude Fazeli and Enayat Rajabi and Leonardo Lezcano and Hendrik Drachsler and Peter Sloep",

year = "2016",

month = dec,

day = "1",

doi = "10.1109/icalt.2016.119",

language = "English",

isbn = "978-1-4673-9042-2",

pages = "423--427",

editor = "J.M. Spector and C.C. Tsai and D.M. Sampson and Kinshuk and R. Huang and N.S. Chen and P. Resta",

booktitle = "2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT)",

publisher = "IEEE",

address = "United States",

note = "2016 IEEE 16th International Conference on Advanced Learning Technologies, ICALT ; Conference date: 25-07-2016 Through 28-07-2016",

url = "http://www.ask4research.info/icalt/2016/",

}

Fazeli, S, Rajabi, E, Lezcano, L, Drachsler, H & Sloep, P 2016, Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study. in JM Spector, CC Tsai, DM Sampson, Kinshuk, R Huang, NS Chen & P Resta (eds), 2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT). IEEE, Piscataway, pp. 423-427, 2016 IEEE 16th International Conference on Advanced Learning Technologies, Austin, TX, United States, 25/07/16. https://doi.org/10.1109/icalt.2016.119

Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study. / Fazeli, Soude; Rajabi, Enayat; Lezcano, Leonardo et al.
2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT). ed. / J.M. Spector; C.C. Tsai; D.M. Sampson; Kinshuk; R. Huang; N.S. Chen; P. Resta. Piscataway: IEEE, 2016. p. 423-427.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Supporting Users of Open Online Courses with Recommendations

T2 - 2016 IEEE 16th International Conference on Advanced Learning Technologies

AU - Fazeli, Soude

AU - Rajabi, Enayat

AU - Lezcano, Leonardo

AU - Drachsler, Hendrik

AU - Sloep, Peter

PY - 2016/12/1

Y1 - 2016/12/1

N2 - Almost all studies on course recommenders in online platforms target closed online platforms that belong to a University or other provider. Recently, a demand has developed that targets open platforms. Such platforms lack rich user profiles with content metadata. Instead they log user interactions. We report on how user interactions and activities tracked in open online learning platforms may generate recommendations. We use data from the OpenU open online learning platform in use by the Open University of the Netherlands to investigate the application of several state-of-the-art recommender algorithms, including a graph-based recommender approach. It appears that user-based and memory-based methods perform better than model-based and factorization methods. Particularly, the graph-based recommender system outperforms the classical approaches on prediction accuracy of recommendations in terms of recall.

AB - Almost all studies on course recommenders in online platforms target closed online platforms that belong to a University or other provider. Recently, a demand has developed that targets open platforms. Such platforms lack rich user profiles with content metadata. Instead they log user interactions. We report on how user interactions and activities tracked in open online learning platforms may generate recommendations. We use data from the OpenU open online learning platform in use by the Open University of the Netherlands to investigate the application of several state-of-the-art recommender algorithms, including a graph-based recommender approach. It appears that user-based and memory-based methods perform better than model-based and factorization methods. Particularly, the graph-based recommender system outperforms the classical approaches on prediction accuracy of recommendations in terms of recall.

KW - recommender systems

KW - collabortive filtering

KW - open online course

KW - performance

KW - accuracy

KW - matrix factorization

U2 - 10.1109/icalt.2016.119

DO - 10.1109/icalt.2016.119

M3 - Conference contribution

SN - 978-1-4673-9042-2

SP - 423

EP - 427

BT - 2016 IEEE 16th International Conference on Advanced Learning Technologies (ICALT)

A2 - Spector, J.M.

A2 - Tsai, C.C.

A2 - Sampson, D.M.

A2 - Kinshuk, null

A2 - Huang, R.

A2 - Chen, N.S.

A2 - Resta, P.

PB - IEEE

CY - Piscataway

Y2 - 25 July 2016 through 28 July 2016

ER -

Supporting Users of Open Online Courses with Recommendations: An Algorithmic Study

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this