Exploring N-gram Features in Clickstream Data for MOOC Learning Achievement Prediction
X. Li, T. Wang, and H. Wang. Database Systems for Advanced Applications: DASFAA 2017 International Workshops: BDMS, BDQM, SeCoP, and DMMOOC, Suzhou, China, March 27-30, 2017, Proceedings, page 328--339. Cham, Springer International Publishing, (2017)
DOI: 10.1007/978-3-319-55705-2_26
Abstract
MOOC is an emerging online educational model in recent years. With the development of big data technology, a huge amount of learning behavior data can be mined by MOOC platforms. Mining learners' past clickstream data to predict their future learning achievement by machine learning technology has become a hot research topic recently. Previous methods only consider the static counting-based features and ignore the correlative, temporal and fragmented nature of MOOC learning behavior, and thus have the limitation in interpretability and prediction accuracy. In this paper, we explore the effectiveness of N-gram features in clickstream data and model the MOOC learning achievement prediction problem as a multiclass classification task which classifies learners into four achievement levels. With extensive experiments on four real-world MOOC datasets, we empirically demonstrate that our methods outperform the state-of-the-art methods significantly.
Description
Exploring N-gram Features in Clickstream Data for MOOC Learning Achievement Prediction | SpringerLink
Database Systems for Advanced Applications: DASFAA 2017 International Workshops: BDMS, BDQM, SeCoP, and DMMOOC, Suzhou, China, March 27-30, 2017, Proceedings
%0 Conference Paper
%1 Li2017
%A Li, Xiao
%A Wang, Ting
%A Wang, Huaimin
%B Database Systems for Advanced Applications: DASFAA 2017 International Workshops: BDMS, BDQM, SeCoP, and DMMOOC, Suzhou, China, March 27-30, 2017, Proceedings
%C Cham
%D 2017
%E Bao, Zhifeng
%E Trajcevski, Goce
%E Chang, Lijun
%E Hua, Wen
%I Springer International Publishing
%K MOOC log-mining sequence-mining
%P 328--339
%R 10.1007/978-3-319-55705-2_26
%T Exploring N-gram Features in Clickstream Data for MOOC Learning Achievement Prediction
%U https://doi.org/10.1007/978-3-319-55705-2_26
%X MOOC is an emerging online educational model in recent years. With the development of big data technology, a huge amount of learning behavior data can be mined by MOOC platforms. Mining learners' past clickstream data to predict their future learning achievement by machine learning technology has become a hot research topic recently. Previous methods only consider the static counting-based features and ignore the correlative, temporal and fragmented nature of MOOC learning behavior, and thus have the limitation in interpretability and prediction accuracy. In this paper, we explore the effectiveness of N-gram features in clickstream data and model the MOOC learning achievement prediction problem as a multiclass classification task which classifies learners into four achievement levels. With extensive experiments on four real-world MOOC datasets, we empirically demonstrate that our methods outperform the state-of-the-art methods significantly.
%@ 978-3-319-55705-2
@inproceedings{Li2017,
abstract = {MOOC is an emerging online educational model in recent years. With the development of big data technology, a huge amount of learning behavior data can be mined by MOOC platforms. Mining learners' past clickstream data to predict their future learning achievement by machine learning technology has become a hot research topic recently. Previous methods only consider the static counting-based features and ignore the correlative, temporal and fragmented nature of MOOC learning behavior, and thus have the limitation in interpretability and prediction accuracy. In this paper, we explore the effectiveness of N-gram features in clickstream data and model the MOOC learning achievement prediction problem as a multiclass classification task which classifies learners into four achievement levels. With extensive experiments on four real-world MOOC datasets, we empirically demonstrate that our methods outperform the state-of-the-art methods significantly.},
added-at = {2017-12-11T04:14:01.000+0100},
address = {Cham},
author = {Li, Xiao and Wang, Ting and Wang, Huaimin},
biburl = {https://www.bibsonomy.org/bibtex/225fe9a0b5de91cefd0005c1981e642d0/brusilovsky},
booktitle = {Database Systems for Advanced Applications: DASFAA 2017 International Workshops: BDMS, BDQM, SeCoP, and DMMOOC, Suzhou, China, March 27-30, 2017, Proceedings},
description = {Exploring N-gram Features in Clickstream Data for MOOC Learning Achievement Prediction | SpringerLink},
doi = {10.1007/978-3-319-55705-2_26},
editor = {Bao, Zhifeng and Trajcevski, Goce and Chang, Lijun and Hua, Wen},
interhash = {3d7f34cedccae0459b6117a40c7dd497},
intrahash = {25fe9a0b5de91cefd0005c1981e642d0},
isbn = {978-3-319-55705-2},
keywords = {MOOC log-mining sequence-mining},
pages = {328--339},
publisher = {Springer International Publishing},
timestamp = {2017-12-11T04:14:01.000+0100},
title = {Exploring N-gram Features in Clickstream Data for MOOC Learning Achievement Prediction},
url = {https://doi.org/10.1007/978-3-319-55705-2_26},
year = 2017
}