Learning object recommendations based on quality and item response theory

Silvia Baldiris, Ramon Fabregat, Sabine Graf, Valentina Tabares, Nestor Duque, Cecilia Avila

Research output: Chapter in Book/Report/Conference proceedingPublished Conference contributionpeer-review

7 Citations (Scopus)

Abstract

Nowadays, teachers and students continue to face the problem to find high quality learning objects for learning and teaching. The purpose of this paper is to introduce an innovative approach, which considers Item Response Theory (IRT) for recommending to students or teachers Learning Objects (LOs) of high quality in the context of the Learning Objects Economy, which is a marketplace for sharing and reuse of LOs. Recommendations provide to teachers or students the needed support for finding high quality learning objects taking advantage of the previous quality evaluations carry out by peers. An evaluation of our approach was carried out in a real scenario which allowed us to verify the applicability of the process for generating good recommendations.

Original languageEnglish
Title of host publicationProceedings - IEEE 14th International Conference on Advanced Learning Technologies, ICALT 2014
EditorsDemetrios G. Sampson, Michael J. Spector, Nian-Shing Chen, Ronghuai Huang, Kinshuk
Pages34-36
Number of pages3
ISBN (Electronic)9781479940387
DOIs
Publication statusPublished - 17 Sep. 2014
Event14th IEEE International Conference on Advanced Learning Technologies, ICALT 2014 - Athens, Greece
Duration: 7 Jul. 20149 Jul. 2014

Publication series

NameProceedings - IEEE 14th International Conference on Advanced Learning Technologies, ICALT 2014

Conference

Conference14th IEEE International Conference on Advanced Learning Technologies, ICALT 2014
Country/TerritoryGreece
CityAthens
Period7/07/149/07/14

Keywords

  • Item response theory
  • learning objects
  • recommendations

Fingerprint

Dive into the research topics of 'Learning object recommendations based on quality and item response theory'. Together they form a unique fingerprint.

Cite this