Combining click-Stream data with NLP tools to better understand MOOC completion

Scott Crossley; Danielle S. Mcnamara; Luc Paquette; Ryan S. Baker; Mihai Dascalu

doi:10.1145/2883851.2883931

Combining click-Stream data with NLP tools to better understand MOOC completion

Scott Crossley, Danielle S. Mcnamara, Luc Paquette, Ryan S. Baker, Mihai Dascalu

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

Abstract

Completion rates for massive open online classes (MOOCs) are notoriously low. Identifying student patterns related to course completion may help to develop interventions that can improve retention and learning outcomes in MOOCs. Previous research predicting MOOC completion has focused on click-stream data, student demographics, and natural language processing (NLP) analyses. However, most of these analyses have not taken full advantage of the multiple types of data available. This study combines click-stream data and NLP approaches to examine if students' on-line activity and the language they produce in the online discussion forum is predictive of successful class completion. We study this analysis in the context of a subsample of 320 students who completed at least one graded assignment and produced at least 50 words in discussion forums, in a MOOC on educational data mining. The findings indicate that a mix of clickstream data and NLP indices can predict with substantial accuracy (78%) whether students complete the MOOC. This predictive power suggests that student interaction data and language data within a MOOC can help us both to understand student retention in MOOCs and to develop automated signals of student success.

Original language	English (US)
Title of host publication	LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact
Subtitle of host publication	Convergence of Communities for Grounding, Implementation, and Validation
Publisher	Association for Computing Machinery
Pages	6-14
Number of pages	9
ISBN (Electronic)	9781450341905
DOIs	https://doi.org/10.1145/2883851.2883931
State	Published - Apr 25 2016
Event	6th International Conference on Learning Analytics and Knowledge, LAK 2016 - Edinburgh, United Kingdom Duration: Apr 25 2016 → Apr 29 2016

Publication series

Name	ACM International Conference Proceeding Series
Volume	25-29-April-2016

Other

Other	6th International Conference on Learning Analytics and Knowledge, LAK 2016
Country/Territory	United Kingdom
City	Edinburgh
Period	4/25/16 → 4/29/16

Keywords

Click-stream data
Educational data mining
Educational success
MOOC
Natural language processing
Predictive analytics
Sentiment analysis

ASJC Scopus subject areas

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

Online availability

10.1145/2883851.2883931

Library availability

Discover UIUC Full Text

Cite this

Crossley, S., Mcnamara, D. S., Paquette, L., Baker, R. S., & Dascalu, M. (2016). Combining click-Stream data with NLP tools to better understand MOOC completion. In LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact: Convergence of Communities for Grounding, Implementation, and Validation (pp. 6-14). (ACM International Conference Proceeding Series; Vol. 25-29-April-2016). Association for Computing Machinery. https://doi.org/10.1145/2883851.2883931

Combining click-Stream data with NLP tools to better understand MOOC completion. / Crossley, Scott; Mcnamara, Danielle S.; Paquette, Luc et al.
LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact: Convergence of Communities for Grounding, Implementation, and Validation. Association for Computing Machinery, 2016. p. 6-14 (ACM International Conference Proceeding Series; Vol. 25-29-April-2016).

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

Crossley, S, Mcnamara, DS, Paquette, L, Baker, RS & Dascalu, M 2016, Combining click-Stream data with NLP tools to better understand MOOC completion. in LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact: Convergence of Communities for Grounding, Implementation, and Validation. ACM International Conference Proceeding Series, vol. 25-29-April-2016, Association for Computing Machinery, pp. 6-14, 6th International Conference on Learning Analytics and Knowledge, LAK 2016, Edinburgh, United Kingdom, 4/25/16. https://doi.org/10.1145/2883851.2883931

Crossley S, Mcnamara DS, Paquette L, Baker RS, Dascalu M. Combining click-Stream data with NLP tools to better understand MOOC completion. In LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact: Convergence of Communities for Grounding, Implementation, and Validation. Association for Computing Machinery. 2016. p. 6-14. (ACM International Conference Proceeding Series). doi: 10.1145/2883851.2883931

Crossley, Scott ; Mcnamara, Danielle S. ; Paquette, Luc et al. / Combining click-Stream data with NLP tools to better understand MOOC completion. LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact: Convergence of Communities for Grounding, Implementation, and Validation. Association for Computing Machinery, 2016. pp. 6-14 (ACM International Conference Proceeding Series).

@inproceedings{cb92ab77d7584ca49788b975c4d36cdb,

title = "Combining click-Stream data with NLP tools to better understand MOOC completion",

abstract = "Completion rates for massive open online classes (MOOCs) are notoriously low. Identifying student patterns related to course completion may help to develop interventions that can improve retention and learning outcomes in MOOCs. Previous research predicting MOOC completion has focused on click-stream data, student demographics, and natural language processing (NLP) analyses. However, most of these analyses have not taken full advantage of the multiple types of data available. This study combines click-stream data and NLP approaches to examine if students' on-line activity and the language they produce in the online discussion forum is predictive of successful class completion. We study this analysis in the context of a subsample of 320 students who completed at least one graded assignment and produced at least 50 words in discussion forums, in a MOOC on educational data mining. The findings indicate that a mix of clickstream data and NLP indices can predict with substantial accuracy (78%) whether students complete the MOOC. This predictive power suggests that student interaction data and language data within a MOOC can help us both to understand student retention in MOOCs and to develop automated signals of student success.",

keywords = "Click-stream data, Educational data mining, Educational success, MOOC, Natural language processing, Predictive analytics, Sentiment analysis",

author = "Scott Crossley and Mcnamara, {Danielle S.} and Luc Paquette and Baker, {Ryan S.} and Mihai Dascalu",

note = "Publisher Copyright: {\textcopyright} 2016 ACM.; 6th International Conference on Learning Analytics and Knowledge, LAK 2016 ; Conference date: 25-04-2016 Through 29-04-2016",

year = "2016",

month = apr,

day = "25",

doi = "10.1145/2883851.2883931",

language = "English (US)",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "6--14",

booktitle = "LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact",

address = "United States",

}

TY - GEN

T1 - Combining click-Stream data with NLP tools to better understand MOOC completion

AU - Crossley, Scott

AU - Mcnamara, Danielle S.

AU - Paquette, Luc

AU - Baker, Ryan S.

AU - Dascalu, Mihai

PY - 2016/4/25

Y1 - 2016/4/25

N2 - Completion rates for massive open online classes (MOOCs) are notoriously low. Identifying student patterns related to course completion may help to develop interventions that can improve retention and learning outcomes in MOOCs. Previous research predicting MOOC completion has focused on click-stream data, student demographics, and natural language processing (NLP) analyses. However, most of these analyses have not taken full advantage of the multiple types of data available. This study combines click-stream data and NLP approaches to examine if students' on-line activity and the language they produce in the online discussion forum is predictive of successful class completion. We study this analysis in the context of a subsample of 320 students who completed at least one graded assignment and produced at least 50 words in discussion forums, in a MOOC on educational data mining. The findings indicate that a mix of clickstream data and NLP indices can predict with substantial accuracy (78%) whether students complete the MOOC. This predictive power suggests that student interaction data and language data within a MOOC can help us both to understand student retention in MOOCs and to develop automated signals of student success.

AB - Completion rates for massive open online classes (MOOCs) are notoriously low. Identifying student patterns related to course completion may help to develop interventions that can improve retention and learning outcomes in MOOCs. Previous research predicting MOOC completion has focused on click-stream data, student demographics, and natural language processing (NLP) analyses. However, most of these analyses have not taken full advantage of the multiple types of data available. This study combines click-stream data and NLP approaches to examine if students' on-line activity and the language they produce in the online discussion forum is predictive of successful class completion. We study this analysis in the context of a subsample of 320 students who completed at least one graded assignment and produced at least 50 words in discussion forums, in a MOOC on educational data mining. The findings indicate that a mix of clickstream data and NLP indices can predict with substantial accuracy (78%) whether students complete the MOOC. This predictive power suggests that student interaction data and language data within a MOOC can help us both to understand student retention in MOOCs and to develop automated signals of student success.

KW - Click-stream data

KW - Educational data mining

KW - Educational success

KW - MOOC

KW - Natural language processing

KW - Predictive analytics

KW - Sentiment analysis

UR - http://www.scopus.com/inward/record.url?scp=84976466253&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976466253&partnerID=8YFLogxK

U2 - 10.1145/2883851.2883931

DO - 10.1145/2883851.2883931

M3 - Conference contribution

AN - SCOPUS:84976466253

T3 - ACM International Conference Proceeding Series

SP - 6

EP - 14

BT - LAK 2016 Conference Proceedings, 6th International Learning Analytics and Knowledge Conference - Enhancing Impact

PB - Association for Computing Machinery

T2 - 6th International Conference on Learning Analytics and Knowledge, LAK 2016

Y2 - 25 April 2016 through 29 April 2016

ER -

Combining click-Stream data with NLP tools to better understand MOOC completion

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this