DC Element | Wert | Sprache |
dc.contributor.author | Shayan, Parisa | |
dc.contributor.author | Atzmueller, Martin | |
dc.contributor.author | Van Zaanen, Menno | |
dc.contributor.editor | Reformat, M. | |
dc.contributor.editor | Zhang, D. | |
dc.contributor.editor | Bourbakis, N.G. | |
dc.date.accessioned | 2023-07-12T06:59:36Z | - |
dc.date.available | 2023-07-12T06:59:36Z | - |
dc.date.issued | 2022 | |
dc.identifier.isbn | 9798350397444 | |
dc.identifier.issn | 1082-3409 | |
dc.identifier.uri | http://osnascholar.ub.uni-osnabrueck.de/handle/unios/72149 | - |
dc.description | Cited by: 0; Conference name: 34th IEEE International Conference on Tools with Artificial Intelligence, ICTAI 2022; Conference date: 31 October 2022 through 2 November 2022; Conference code: 188065 | |
dc.description.abstract | This article investigates the influence of time on features for the prediction of user dropout in an online training platform. Specifically, we target a comparison between the two time measurements: activity-based versus duration-based. Considering time, we utilize features in different groups: either activity-based features for activities or duration-based features for duration, as well as the start-based, action-type-based, and course-based features for both time measurements. The most surprising aspect of the results is the high accuracy of the classifiers from the tenth activity (which corresponds to almost half a day on average) onward. While the action-type-based and the course-based features have a major influence on dropout, the start-based features are only influential in the classifiers that use information of activities at beginning. In addition, the activity-based features have only a minor impact in the middle of the course whilst the duration-based features have a major influence throughout the course. © 2022 IEEE. | |
dc.language.iso | en | |
dc.publisher | IEEE Computer Society | |
dc.relation.ispartof | Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI | |
dc.subject | Activity-based | |
dc.subject | Classification (of information) | |
dc.subject | Data mining | |
dc.subject | Educational Data Mining | |
dc.subject | Feature Construction | |
dc.subject | Forecasting | |
dc.subject | High-accuracy | |
dc.subject | Online training | |
dc.subject | Time measurement | |
dc.subject | Training platform | |
dc.subject | User Dropout Prediction | |
dc.subject | User Modeling | |
dc.subject | User Modelling | |
dc.title | Assessing the Influence of Time on Features for the Prediction of User Dropout | |
dc.type | conference paper | |
dc.identifier.doi | 10.1109/ICTAI56018.2022.00156 | |
dc.identifier.scopus | 2-s2.0-85156113407 | |
dc.identifier.url | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85156113407&doi=10.1109%2fICTAI56018.2022.00156&partnerID=40&md5=8f8b97547217d0e5a66a86545c046c96 | |
dc.description.volume | 2022-October | |
dc.description.startpage | 1022 – 1027 | |
dcterms.isPartOf.abbreviation | Proc. Int. Conf. Tools Artif. Intell. ICTAI | |
local.import.remains | affiliations : Tilburg University, TSHD, CSAI, Tilburg, Netherlands; Osnabrück University & Dfki, Semantic Information Systems Group, Osnabrück, Germany; South African Centre for Digital Language Resources, Potchefstroom, South Africa | |
local.import.remains | publication_stage : Final | |
crisitem.author.dept | FB 06 - Mathematik/Informatik/Physik | - |
crisitem.author.deptid | fb6 | - |
crisitem.author.parentorg | Universität Osnabrück | - |
crisitem.author.netid | AtMa176 | - |