TY - GEN
T1 - Combining click-Stream data with NLP tools to better understand MOOC completion
AU - Crossley, Scott
AU - McNamara, Danielle
AU - Paquette, Luc
AU - Baker, Ryan S.
AU - Dascalu, Mihai
N1 - Publisher Copyright:
© 2016 ACM.
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 -