-
-
Author(s): Verbert, Katrien; Drachsler, Hendrik; Manouselis, Nikos; Wolpers, Martin; Vuorikari, Riina; Duval, Erik
Title: Dataset-driven research for improving recommender systems for learning
In: Long, Phillip; Siemens, George; Conole, Gráinne; Gašević, Dragan (Hrsg.): Proceedings of the 1st International Conference on Learning Analytics and Knowledge (LAK '11), Banff, Alberta, Canada - February 27 - March 01, 2011, New York; NY: Association for Computing Machinery, 2011 , S. 44-53
DOI: 10.1145/2090116.2090122
Publication Type: 4. Beiträge in Sammelwerken; Sammelband (keine besondere Kategorie)
Language: Englisch
Abstract: In the world of recommender systems, it is a common practice to use public available datasets from different application environments (e.g. MovieLens, Book-Crossing, or Each-Movie) in order to evaluate recommendation algorithms. These datasets are used as benchmarks to develop new recommendation algorithms and to compare them to other algorithms in given settings. In this paper, we explore datasets that capture learner interactions with tools and resources. We use the datasets to evaluate and compare the performance of different recommendation algorithms for learning. We present an experimental comparison of the accuracy of several collaborative filtering algorithms applied to these TEL datasets and elaborate on implicit relevance data, such as downloads and tags, that can be used to improve the performance of recommendation algorithms. (Orig.)