Downloads: 28

Files in This Item:
File Description SizeFormat 
ICCE2020.1_342.pdf601 kBAdobe PDFView/Open
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAKÇAPINAR, Gökhanen
dc.contributor.authorHASNINE, Nehal Mohammaden
dc.contributor.authorMAJUMDAR, Rwitajiten
dc.contributor.authorCHEN, Alice Mei-Rongen
dc.contributor.authorFLAGANAN, Brendanen
dc.contributor.authorOGATA, Hiroakien
dc.contributor.alternative緒方, 広明ja
dc.date.accessioned2020-12-15T00:52:50Z-
dc.date.available2020-12-15T00:52:50Z-
dc.date.issued2020-11-23-
dc.identifier.isbn9789869721455-
dc.identifier.urihttp://hdl.handle.net/2433/259783-
dc.description28th International Conference on Computers in Education, 23-27 November 2020, Web conference.en
dc.description.abstractIn this study, approximately 2 million click-stream data of 1346 students in the eBook platform were analyzed aiming to explore the temporal study patterns of the students followed during the lectures. The data used in the study collected from Kyushu University, Japan with the help of a digital textbook reader called BookRoll. Students used BookRoll for reading learning materials in and out of the class. To analyze the data we first, converted reading sessions into the sequence data which represents student’s weekly reading behavior, then we clustered students based on their study patterns. Our results revealed that three groups of students can be extracted with similar study patterns. Most of the students in Cluster 1 viewed the learning materials only during the class, without previewing and reviewing them. Students in Cluster 2 previewed the learning materials before the class, viewed learning materials during the class, and also reviewed after the class. Students in Cluster 3 viewed the learning materials during the class in the beginning but they became inactive over the period of time (week by week). Our study also showed how learning analytics can be used to understand students' study patterns which are difficult to do with self-report data. These results can help instructors while designing their courses.en
dc.format.mimetypeapplication/pdf-
dc.language.isoeng-
dc.publisherAsia-Pacific Society for Computers in Education (APSCE)en
dc.rightsCopyright 2020 Asia-Pacific Society for Computers in Education.en
dc.rights許諾条件に基づいて掲載しています。ja
dc.subjectsequence miningen
dc.subjectclusteringen
dc.subjectreading logsen
dc.subjecteBooken
dc.subjecteducational data miningen
dc.subjectlearning analyticsen
dc.titleExploring Temporal Study Patterns in eBook-based Learningen
dc.typeconference paper-
dc.type.niitypeConference Paper-
dc.identifier.jtitle28th International Conference on Computers in Education Conference Proceedings-
dc.identifier.volume1-
dc.identifier.spage342-
dc.identifier.epage347-
dc.textversionpublisher-
dc.addressDepartment of Computer Education & Instructional Technology, Hacettepe Universityen
dc.addressResearch Center for Computing and Multimedia Studies, Hosei Universityen
dc.addressAcademic Center for Computing and Media Studies, Kyoto Universityen
dc.addressAcademic Center for Computing and Media Studies, Kyoto Universityen
dc.addressAcademic Center for Computing and Media Studies, Kyoto Universityen
dc.addressAcademic Center for Computing and Media Studies, Kyoto Universityen
dcterms.accessRightsopen access-
datacite.awardNumber16H06304-
jpcoar.funderName日本学術振興会ja
jpcoar.funderName.alternativeJapan Society for the Promotion of Science (JSPS)en
Appears in Collections:Journal Articles

Show simple item record

Export to RefWorks


Export Format: 


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.