Assessing the Influence of Time on Features for the Prediction of User Dropout

Autor(en): Shayan, Parisa
Atzmueller, Martin 
Van Zaanen, Menno
Herausgeber: Reformat, M.
Zhang, D.
Bourbakis, N.G.
Stichwörter: Activity-based; Classification (of information); Data mining; Educational Data Mining; Feature Construction; Forecasting; High-accuracy; Online training; Time measurement; Training platform; User Dropout Prediction; User Modeling; User Modelling
Erscheinungsdatum: 2022
Herausgeber: IEEE Computer Society
Journal: Proceedings - International Conference on Tools with Artificial Intelligence, ICTAI
Volumen: 2022-October
Startseite: 1022 – 1027
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.
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
ISBN: 9798350397444
ISSN: 1082-3409
DOI: 10.1109/ICTAI56018.2022.00156
Externe URL:

Show full item record

Google ScholarTM