Année : 2008
Lieu de publication de l'article :

Résumé de l'article

The decision onwhat item to learn next in a course can be supportedby a recommender system (RS), which aims at making the learningprocess more efficient and effective. However, learners and learningactivities frequently change over time. The question is: how aretimely appropriate recommendations of learning resources actuallyevaluated and how can they be compared?Researchers have found that, in addition to a standardized datasetdefinition, there is also a lack of standardized definitions of evalua-tion procedures for RS in the area of Technology Enhanced Learning.This paper argues that, in a closed-course setting, a time-dependentsplit into the training set and test set is more appropriate than theusual cross-validation to evaluate the Top-N recommended learningresources at various points in time. Moreover, a new measure is in-troduced to determine the timeliness deviation between the point intime of an item recommendation and the point in time of the actualaccess by the user. Different recommender algorithms, includingtwo novel ones, are evaluated with the time-dependent evaluationframework and the results, as well as the appropriateness of theframework, are discussed.CCS CONCEPTS• Information systems→ Evaluation of retrieval results; Rec-ommender systems; • Applied computing → Computer-assistedinstruction;KEYWORDSTime-Dependent Evaluation Framework, Educational RecommenderSystems, Timeliness DeviationACM Reference Format:Christopher Krauss, Agathe Merceron, and Stefan Arbanowski. 2019. TheTimeliness Deviation: A novel Approach to Evaluate Educational Recom-mender Systems for Closed-Courses. In The 9th International Learning Ana-lytics & Knowledge Conference (LAK19), March 4–8, 2019, Tempe, AZ, USA.ACM,NewYork, NY, USA, 10 pages. https://doi.org/10.1145/3303772.3303774Permission to make digital or hard copies of all or part of this work for personal orclassroom use is granted without fee provided that copies are not made or distributedfor profit or commercial advantage and that copies bear this notice and the full citationon the first page. Copyrights for components of this work owned by others than theauthor(s) must be honored. Abstracting with credit is permitted. To copy otherwise, orrepublish, to post on servers or to redistribute to lists, requires prior specific permissionand/or a fee. Request permissions from permissions@acm.org.LAK19, March 4–8, 2019, Tempe, AZ, USA© 2019 Copyright held by the owner/author(s). Publication rights licensed to ACM.ACM ISBN 978-1-4503-6256-6/19/03. . . $15.00https://doi.org/10.1145/3303772.3303774

Mots-clés

Human factors and ergonomics,SIGCSE,Computer science,Relevance,Genera,Paper,IFIP Working Group 2.1,International Federation for Information Processing,One Thousand,Computer scientist,Lively Kernel,Computer Systems,Educational Curriculum,