Towards a Social Trust-Aware Recommender for Teachers

Abstract

Abstract. Online communities and networked learning provide teachers with social learning opportunities, allowing them to interact and collaborate with others in order to develop their personal and professional skills. However, with the large number of learning resources produced every day, teachers need to find out what are the most suitable ones for them. In this paper, we introduce recommender systems as a potential solution to this. The setting is the Open Discovery Space (ODS) project. Unfortunately, due to the sparsity of the educational datasets most educational recommender systems cannot make accurate recommendations. To overcome this problem, we propose to enhance a trustbased recommender algorithm with social data obtained from monitoring the activities of teachers within the ODS platform. In this article, we outline the requirements of the ODS recommender system based on experiences reported in related TEL recommender system studies. In addition, we provide empirical evidence from a survey study with stakeholders of the ODS project to support the requirements identified from a literature study. Finally, we present an agenda for further research intended to find out which recommender system should ultimately be deployed in the ODS platform.

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

“…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.…”

“…A fundamental component towards the goal of exposing social data and paradata as LD is provided by the SIOC (Semantically-Interlinked Online Communities) initiative 50 . SIOC [32] is an ontology to describe user-generated content on forums, weblogs, and web2.0 sites, and link online communities.…”

Αξιοποίηση Συστημάτων Συστάσεων Στο Μαθησιακό Σχεδιασμό

“…Ο τύπος της αξιολόγησης που πραγματοποιήθηκε σύμφωνα με την κατάταξη των Erdt, Fernandez, & Rensing (2015) είναι αξιολόγηση εκτός σύνδεσης (offline experiment). Οι (Fazeli, Drachsler, Brouns, & Sloep, 2014) προτείνουν ένα ΣΣ για την υποστήριξη των εκπαιδευτικών στη διαμοίραση ΜΑ με την εξατομικευμένη σύσταση ΜΑ σύμφωνα με το δίκτυο εμπιστοσύνης (trust networks) που διαμορφώνεται γύρω από αυτούς. Για την υλοποίηση του ΣΣ εφάρμοσαν μια προσέγγιση ΣΦ, ενισχυμένη με δεδομένα που προέρχονται από τις κοινωνικές δραστηριότητες των εκπαιδευτικών (π.χ.…”

“…δημιουργία σελιδοδεικτών, ετικετών και αξιολογήσεων) στην πλατφόρμα Open Discovery Space (ODS). Οι Fazeli et al (2014) πραγματοποίησαν μια χρηστο-κεντρική (user study) αξιολόγηση σύμφωνα με την κατάταξη των (Erdt et al, 2015) με σκοπό να αποτιμήσουν τη σπουδαιότητα και τη χρηστικότητα των κοινωνικών δραστηριοτήτων σε online πλατφόρμα και τη χρήση ΣΣ στο πλαίσιο αυτής. Η αξιολόγηση πραγματοποιήθηκε στο πλαίσιο του θερινού σχολείου ODS (Open Discovery Space) με συμμετοχή 33 εκπαιδευτικών.…”

Using Trust of Social Ties for Recommendation

“…Jin et al [28] designed a trustbased top-k recommender system, which computed the trust values between users from users' interest similarity. Fazeli et al [29] proposed a trust-based recommender algorithm with social data obtained from monitoring the Open Discovery Space (ODS), which is a platform for sharing eLearning resources online.…”