Dataset-driven research for improving recommender systems for learning

Verbert, Katrien; Drachsler, Hendrik; Manouselis, Nikos; Wolpers, Martin; Vuorikari, Riina; Duval, Erik

doi:10.1145/2090116.2090122

Cited by 142 publications

(113 citation statements)

References 30 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…in forms of 5-star ratings explicitly expressed by users. As one of the popular similarity measures, we used the Jaccard coefficient since the data includes implicit user feedback in binary format [21]. In this study, we use both user-based and item-based CF algorithms since we make use of users' interactions and activities.…”

Section: Memory-based Recommender Systemsmentioning

confidence: 99%

User-Centric Evaluation of Recommender Systems in Social Learning Platforms: Accuracy is Just the Tip of the Iceberg

Fazeli

Drachsler

Bitter-Rijpkema

et al. 2018

IEEE Trans. Learning Technol.

Self Cite

View full text Add to dashboard Cite

Abstract-Recommender systems provide users with content they might be interested in. Conventionally, recommender systems are evaluated mostly by using prediction accuracy metrics only. But the ultimate goal of a recommender system is to increase user satisfaction. Therefore, evaluations that measure user satisfaction should be also performed before deploying a recommender system to a real target environment. Such evaluations are laborious and complicated compared to the traditional, data-centric evaluations, though. In this study, we investigate the added value of user-centric evaluations and how user satisfaction of a recommender system is related to its performance in terms of accuracy metrics. We conduct both a data-centric evaluation and a user-centric evaluation on the same data collected from an authentic social learning platform. Our findings suggest that user-centric evaluation results are not necessarily in line with data-centric evaluation results. We conclude that the traditional evaluation of recommender systems in terms of prediction accuracy does not suffice to judge performance of recommender systems on the user side. Moreover, the user-centric evaluation provides valuable insights on how candidate algorithms perform on each of the five quality metrics: usefulness, accuracy, novelty, diversity, and serendipity of the recommendations.

show abstract

Section: Memory-based Recommender Systemsmentioning

confidence: 99%

User-Centric Evaluation of Recommender Systems in Social Learning Platforms: Accuracy is Just the Tip of the Iceberg

Fazeli

Drachsler

Bitter-Rijpkema

et al. 2018

IEEE Trans. Learning Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, the dataTEL project published an initial list of 20 available TEL datasets for research and compared the different datasets according to certain criteria (see Table 1) [46]. With this initiative the amount of available TEL datasets has increased and initial comparison study's are emerging that use the same dataset for different personalisation techniques [47] [48][49] [50]. The overall aim of the dataTEL initiative is to make different personalisation approaches more comparable to gain a body of knowledge about the effects of personalisation on learning.…”

Section: Tel Resource Data Sharing On the Web -State Of The Artmentioning

confidence: 99%

“…Examples for event types are "send", "update" or "select". CAM is used in a couple of European projects such as ROLE 47 …”

Section: Contextualized Attention Metadata (Cam)mentioning

confidence: 99%

A Survey on Linked Data and the Social Web as Facilitators for TEL Recommender Systems

Dietze

Drachsler

Giordano

2014

Recommender Systems for Technology Enhanced Learning

Self Cite

View full text Add to dashboard Cite

Abstract. Personalisation, adaptation and recommendation are central features of TEL environments. In this context, information retrieval techniques are applied as part of TEL recommender systems to filter and recommend learning resources or peer learners according to user preferences and requirements. However, the suitability and scope of possible recommendations is fundamentally dependent on the quality and quantity of available data, for instance, metadata about TEL resources as well as users. On the other hand, throughout the last years, the Linked Data (LD) movement has succeeded to provide a vast body of well-interlinked and publicly accessible Web data. This in particular includes Linked Data of explicit or implicit educational nature. The potential of LD to facilitate TEL recommender systems research and practice is discussed in this paper. In particular, an overview of most relevant LD sources and techniques is provided, together with a discussion of their potential for the TEL domain in general and TEL recommender systems in particular. Results from highly related European projects are presented and discussed together with an analysis of prevailing challenges and preliminary solutions.Keywords. Linked Data, Education, Semantic Web, Technology-Enhanced Learning, Data Consolidation, Data Integration IntroductionAs personalisation, adaptation and recommendation are central features of TEL environments, TEL recommender systems apply information retrieval techniques to filter and deliver learning resources according to user preferences and requirements. While the suitability and scope of possible recommendations is fundamentally dependent on the quality and quantity of available data, e.g., data about learners, and in particular metadata about TEL resources, the landscape of standards and approaches currently exploited to share and reuse educational data is highly fragmented.

show abstract

“…They are increasingly used in technology-enhanced learning research as a core objective of learning analytics (Chatti et al 2012, Verbert et al 2011. Most recommender systems rely on collaborative filtering, a method that makes automated predictions about the interests of a user, based on information collected from many users.…”

Section: Learning Analyticsmentioning

confidence: 99%