File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Conference Paper: WPSS: dropout prediction for MOOCs using course progress normalization and subset selection

TitleWPSS: dropout prediction for MOOCs using course progress normalization and subset selection
Authors
Issue Date2018
PublisherACM.
Citation
The 5th Annual ACM Conference on Learning at Scale, London, UK, 26-28 June 2018, Article No. 29 How to Cite?
AbstractThere are existing multi-MOOC level dropout prediction research in which many MOOCs' data are involved. This generated good results, but there are two potential problems. On one hand, it is inappropriate to use which week students are in to select training data because courses are with different durations. On the other hand, using all other existing data can be computationally expensive and inapplicable in practice. To solve these problems, we propose a model called WPSS (WPercent and Subset Selection) which combines the course progress normalization parameter wpercent and subset selection. 10 MOOCs offered by The University of Hong Kong are involved and experiments are in the multi-MOOC level. The best performance of WPSS is obtained in neural network when 50% of training data is selected (average AUC of 0.9334). Average AUC is 0.8833 for traditional model without wpercent and subset selection in the same dataset.
Persistent Identifierhttp://hdl.handle.net/10722/259121
ISBN

 

DC FieldValueLanguage
dc.contributor.authorChai, Y-
dc.contributor.authorLei, CU-
dc.contributor.authorHu, X-
dc.contributor.authorKwok, YK-
dc.date.accessioned2018-09-03T04:01:48Z-
dc.date.available2018-09-03T04:01:48Z-
dc.date.issued2018-
dc.identifier.citationThe 5th Annual ACM Conference on Learning at Scale, London, UK, 26-28 June 2018, Article No. 29-
dc.identifier.isbn978-1-4503-5886-6-
dc.identifier.urihttp://hdl.handle.net/10722/259121-
dc.description.abstractThere are existing multi-MOOC level dropout prediction research in which many MOOCs' data are involved. This generated good results, but there are two potential problems. On one hand, it is inappropriate to use which week students are in to select training data because courses are with different durations. On the other hand, using all other existing data can be computationally expensive and inapplicable in practice. To solve these problems, we propose a model called WPSS (<u>WP</u>ercent and <u>S</u>ubset <u>S</u>election) which combines the course progress normalization parameter wpercent and subset selection. 10 MOOCs offered by The University of Hong Kong are involved and experiments are in the multi-MOOC level. The best performance of WPSS is obtained in neural network when 50% of training data is selected (average AUC of 0.9334). Average AUC is 0.8833 for traditional model without wpercent and subset selection in the same dataset.-
dc.languageeng-
dc.publisherACM.-
dc.relation.ispartofL@S '18 Proceedings of the Fifth Annual ACM Conference on Learning at Scale-
dc.titleWPSS: dropout prediction for MOOCs using course progress normalization and subset selection-
dc.typeConference_Paper-
dc.identifier.emailChai, Y: yqchai@hku.hk-
dc.identifier.emailLei, CU: culei@hku.hk-
dc.identifier.emailHu, X: xiaoxhu@hku.hk-
dc.identifier.emailKwok, YK: ykwok@hku.hk-
dc.identifier.authorityLei, CU=rp01908-
dc.identifier.authorityHu, X=rp01711-
dc.identifier.authorityKwok, YK=rp00128-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1145/3231644.3231687-
dc.identifier.hkuros289580-
dc.identifier.spageArticle No. 29-
dc.identifier.epageArticle No. 29-
dc.publisher.placeNew York, NY-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats