Facilitating course recommendations by word2vec paradigm through social tags

Jingjing Wang; Haoran Xie; Oliver Tat Sheung Au; Lap Kei Lee; Di Zou; Fu Lee Wang

doi:10.1007/978-981-33-4594-2_20

Facilitating course recommendations by word2vec paradigm through social tags

Jingjing Wang, Haoran Xie, Oliver Tat Sheung Au, Lap Kei Lee, Di Zou, Fu Lee Wang

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

Abstract

As an important educational form, online learning has attracted millions of registered learners, and a huge number of courses are available online. However, it is challenging for learners to identify appropriate courses from a large course pool due to the difficulties of mapping complex learning needs to the high-level course semantics. Several studies in the field of Natural Language Processing (NLP) have recently gained promising performance in capturing the semantic information. In this study, we use these NLP techniques to understand the semantics of learning needs and courses. Specifically, we model users’ historical course records as word sentences using skip-gram with negative sampling to obtain course semantics. Furthermore, we introduce Laplacian Eigenmaps as the objective function and integrate the course social tags and course-user interaction as penalty factors to fine-tune the course vectors, especially the courses of different categories but similar contexts. The result verifies that the proposed method is effective for recommending suitable courses for users.

Original language	English
Title of host publication	Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers
Editors	Lap-Kei Lee, Leong Hou U, Fu Lee Wang, Simon K. Cheung, Oliver Au, Kam Cheong Li
Pages	239-247
Number of pages	9
DOIs	https://doi.org/10.1007/978-981-33-4594-2_20
Publication status	Published - 2020
Event	5th International Conference on Technology in Education, ICTE 2020 - Macao, China Duration: 19 Aug 2020 → 22 Aug 2020

Publication series

Name	Communications in Computer and Information Science
Volume	1302
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	5th International Conference on Technology in Education, ICTE 2020
Country/Territory	China
City	Macao
Period	19/08/20 → 22/08/20

Keywords

Recommender systems
Skip-gram technique
Word embedding
Word2vec

Access to Document

10.1007/978-981-33-4594-2_20

Cite this

Wang, J., Xie, H., Au, O. T. S., Lee, L. K., Zou, D., & Wang, F. L. (2020). Facilitating course recommendations by word2vec paradigm through social tags. In L.-K. Lee, L. H. U, F. L. Wang, S. K. Cheung, O. Au, & K. C. Li (Eds.), Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers (pp. 239-247). (Communications in Computer and Information Science; Vol. 1302). https://doi.org/10.1007/978-981-33-4594-2_20

Wang, Jingjing ; Xie, Haoran ; Au, Oliver Tat Sheung et al. / Facilitating course recommendations by word2vec paradigm through social tags. Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers. editor / Lap-Kei Lee ; Leong Hou U ; Fu Lee Wang ; Simon K. Cheung ; Oliver Au ; Kam Cheong Li. 2020. pp. 239-247 (Communications in Computer and Information Science).

@inproceedings{fbe139bef3e34644b01b1bdd4c29c8e9,

title = "Facilitating course recommendations by word2vec paradigm through social tags",

abstract = "As an important educational form, online learning has attracted millions of registered learners, and a huge number of courses are available online. However, it is challenging for learners to identify appropriate courses from a large course pool due to the difficulties of mapping complex learning needs to the high-level course semantics. Several studies in the field of Natural Language Processing (NLP) have recently gained promising performance in capturing the semantic information. In this study, we use these NLP techniques to understand the semantics of learning needs and courses. Specifically, we model users{\textquoteright} historical course records as word sentences using skip-gram with negative sampling to obtain course semantics. Furthermore, we introduce Laplacian Eigenmaps as the objective function and integrate the course social tags and course-user interaction as penalty factors to fine-tune the course vectors, especially the courses of different categories but similar contexts. The result verifies that the proposed method is effective for recommending suitable courses for users.",

keywords = "Recommender systems, Skip-gram technique, Word embedding, Word2vec",

author = "Jingjing Wang and Haoran Xie and Au, {Oliver Tat Sheung} and Lee, {Lap Kei} and Di Zou and Wang, {Fu Lee}",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; 5th International Conference on Technology in Education, ICTE 2020 ; Conference date: 19-08-2020 Through 22-08-2020",

year = "2020",

doi = "10.1007/978-981-33-4594-2_20",

language = "English",

isbn = "9789813345935",

series = "Communications in Computer and Information Science",

pages = "239--247",

editor = "Lap-Kei Lee and U, {Leong Hou} and Wang, {Fu Lee} and Cheung, {Simon K.} and Oliver Au and Li, {Kam Cheong}",

booktitle = "Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers",

}

Wang, J, Xie, H, Au, OTS, Lee, LK, Zou, D & Wang, FL 2020, Facilitating course recommendations by word2vec paradigm through social tags. in L-K Lee, LH U, FL Wang, SK Cheung, O Au & KC Li (eds), Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers. Communications in Computer and Information Science, vol. 1302, pp. 239-247, 5th International Conference on Technology in Education, ICTE 2020, Macao, China, 19/08/20. https://doi.org/10.1007/978-981-33-4594-2_20

Facilitating course recommendations by word2vec paradigm through social tags. / Wang, Jingjing; Xie, Haoran; Au, Oliver Tat Sheung et al.
Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers. ed. / Lap-Kei Lee; Leong Hou U; Fu Lee Wang; Simon K. Cheung; Oliver Au; Kam Cheong Li. 2020. p. 239-247 (Communications in Computer and Information Science; Vol. 1302).

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

TY - GEN

T1 - Facilitating course recommendations by word2vec paradigm through social tags

AU - Wang, Jingjing

AU - Xie, Haoran

AU - Au, Oliver Tat Sheung

AU - Lee, Lap Kei

AU - Zou, Di

AU - Wang, Fu Lee

PY - 2020

Y1 - 2020

N2 - As an important educational form, online learning has attracted millions of registered learners, and a huge number of courses are available online. However, it is challenging for learners to identify appropriate courses from a large course pool due to the difficulties of mapping complex learning needs to the high-level course semantics. Several studies in the field of Natural Language Processing (NLP) have recently gained promising performance in capturing the semantic information. In this study, we use these NLP techniques to understand the semantics of learning needs and courses. Specifically, we model users’ historical course records as word sentences using skip-gram with negative sampling to obtain course semantics. Furthermore, we introduce Laplacian Eigenmaps as the objective function and integrate the course social tags and course-user interaction as penalty factors to fine-tune the course vectors, especially the courses of different categories but similar contexts. The result verifies that the proposed method is effective for recommending suitable courses for users.

AB - As an important educational form, online learning has attracted millions of registered learners, and a huge number of courses are available online. However, it is challenging for learners to identify appropriate courses from a large course pool due to the difficulties of mapping complex learning needs to the high-level course semantics. Several studies in the field of Natural Language Processing (NLP) have recently gained promising performance in capturing the semantic information. In this study, we use these NLP techniques to understand the semantics of learning needs and courses. Specifically, we model users’ historical course records as word sentences using skip-gram with negative sampling to obtain course semantics. Furthermore, we introduce Laplacian Eigenmaps as the objective function and integrate the course social tags and course-user interaction as penalty factors to fine-tune the course vectors, especially the courses of different categories but similar contexts. The result verifies that the proposed method is effective for recommending suitable courses for users.

KW - Recommender systems

KW - Skip-gram technique

KW - Word embedding

KW - Word2vec

UR - http://www.scopus.com/inward/record.url?scp=85098238006&partnerID=8YFLogxK

U2 - 10.1007/978-981-33-4594-2_20

DO - 10.1007/978-981-33-4594-2_20

M3 - Conference contribution

AN - SCOPUS:85098238006

SN - 9789813345935

T3 - Communications in Computer and Information Science

SP - 239

EP - 247

BT - Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers

A2 - Lee, Lap-Kei

A2 - U, Leong Hou

A2 - Wang, Fu Lee

A2 - Cheung, Simon K.

A2 - Au, Oliver

A2 - Li, Kam Cheong

T2 - 5th International Conference on Technology in Education, ICTE 2020

Y2 - 19 August 2020 through 22 August 2020

ER -

Wang J, Xie H, Au OTS, Lee LK, Zou D, Wang FL. Facilitating course recommendations by word2vec paradigm through social tags. In Lee LK, U LH, Wang FL, Cheung SK, Au O, Li KC, editors, Technology in Education. Innovations for Online Teaching and Learning - 5th International Conference, ICTE 2020, Revised Selected Papers. 2020. p. 239-247. (Communications in Computer and Information Science). doi: 10.1007/978-981-33-4594-2_20

Facilitating course recommendations by word2vec paradigm through social tags

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this