Populating learning object repositories with hidden internal quality information

Cristian Cechinel, Sandro Silva Da Camargo, Xavier Ochoa, Salvador Sánchez Alonso, Miguel Ángel Sicilia

Research output: Contribution to journalConference article

Abstract

It is known that current Learning Object Repositories adopt strategies for quality assessment of their resources that rely on the impressions of quality given by the members of the repository community. Although this strategy can be considered effective at some extent, the number of resources inside repositories tends to increase more rapidly than the number of evaluations given by this community, thus leaving several resources of the repository without any quality assessment. The present work describes the results of an experiment for automatically generate quality information about learning resources inside repositories through the use of Artificial Neural Networks models. We were able to generate models for classifying resources between good and not-good with accuracies that vary from 50% to 80% depending on the given subset. The preliminary results found here point out the feasibility of such approach and can be used as a starting point for the pursuit of automatically generation of internal quality information about resources inside repositories.

Original languageEnglish (US)
Pages (from-to)11-22
Number of pages12
JournalCEUR Workshop Proceedings
Volume896
StatePublished - Dec 1 2012
Event2nd Workshop on Recommender Systems in Technology Enhanced Learning 2012, RecSysTEL 2012 - In Conjunction with the 7th European Conference on Technology Enhanced Learning, EC-TEL 2012 - Saarbrucken, Germany
Duration: Sep 18 2012Sep 19 2012

Fingerprint

Neural networks
Experiments

Keywords

  • Artificial neural networks
  • Learning object repositories
  • Learning objects
  • MERLOT
  • Ranking mechanisms
  • Ratings

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Cechinel, C., Da Camargo, S. S., Ochoa, X., Alonso, S. S., & Sicilia, M. Á. (2012). Populating learning object repositories with hidden internal quality information. CEUR Workshop Proceedings, 896, 11-22.

Populating learning object repositories with hidden internal quality information. / Cechinel, Cristian; Da Camargo, Sandro Silva; Ochoa, Xavier; Alonso, Salvador Sánchez; Sicilia, Miguel Ángel.

In: CEUR Workshop Proceedings, Vol. 896, 01.12.2012, p. 11-22.

Research output: Contribution to journalConference article

Cechinel, C, Da Camargo, SS, Ochoa, X, Alonso, SS & Sicilia, MÁ 2012, 'Populating learning object repositories with hidden internal quality information', CEUR Workshop Proceedings, vol. 896, pp. 11-22.
Cechinel C, Da Camargo SS, Ochoa X, Alonso SS, Sicilia MÁ. Populating learning object repositories with hidden internal quality information. CEUR Workshop Proceedings. 2012 Dec 1;896:11-22.
Cechinel, Cristian ; Da Camargo, Sandro Silva ; Ochoa, Xavier ; Alonso, Salvador Sánchez ; Sicilia, Miguel Ángel. / Populating learning object repositories with hidden internal quality information. In: CEUR Workshop Proceedings. 2012 ; Vol. 896. pp. 11-22.
@article{096250b33b83442f931ae3d030a75a1e,
title = "Populating learning object repositories with hidden internal quality information",
abstract = "It is known that current Learning Object Repositories adopt strategies for quality assessment of their resources that rely on the impressions of quality given by the members of the repository community. Although this strategy can be considered effective at some extent, the number of resources inside repositories tends to increase more rapidly than the number of evaluations given by this community, thus leaving several resources of the repository without any quality assessment. The present work describes the results of an experiment for automatically generate quality information about learning resources inside repositories through the use of Artificial Neural Networks models. We were able to generate models for classifying resources between good and not-good with accuracies that vary from 50{\%} to 80{\%} depending on the given subset. The preliminary results found here point out the feasibility of such approach and can be used as a starting point for the pursuit of automatically generation of internal quality information about resources inside repositories.",
keywords = "Artificial neural networks, Learning object repositories, Learning objects, MERLOT, Ranking mechanisms, Ratings",
author = "Cristian Cechinel and {Da Camargo}, {Sandro Silva} and Xavier Ochoa and Alonso, {Salvador S{\'a}nchez} and Sicilia, {Miguel {\'A}ngel}",
year = "2012",
month = "12",
day = "1",
language = "English (US)",
volume = "896",
pages = "11--22",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "CEUR-WS",

}

TY - JOUR

T1 - Populating learning object repositories with hidden internal quality information

AU - Cechinel, Cristian

AU - Da Camargo, Sandro Silva

AU - Ochoa, Xavier

AU - Alonso, Salvador Sánchez

AU - Sicilia, Miguel Ángel

PY - 2012/12/1

Y1 - 2012/12/1

N2 - It is known that current Learning Object Repositories adopt strategies for quality assessment of their resources that rely on the impressions of quality given by the members of the repository community. Although this strategy can be considered effective at some extent, the number of resources inside repositories tends to increase more rapidly than the number of evaluations given by this community, thus leaving several resources of the repository without any quality assessment. The present work describes the results of an experiment for automatically generate quality information about learning resources inside repositories through the use of Artificial Neural Networks models. We were able to generate models for classifying resources between good and not-good with accuracies that vary from 50% to 80% depending on the given subset. The preliminary results found here point out the feasibility of such approach and can be used as a starting point for the pursuit of automatically generation of internal quality information about resources inside repositories.

AB - It is known that current Learning Object Repositories adopt strategies for quality assessment of their resources that rely on the impressions of quality given by the members of the repository community. Although this strategy can be considered effective at some extent, the number of resources inside repositories tends to increase more rapidly than the number of evaluations given by this community, thus leaving several resources of the repository without any quality assessment. The present work describes the results of an experiment for automatically generate quality information about learning resources inside repositories through the use of Artificial Neural Networks models. We were able to generate models for classifying resources between good and not-good with accuracies that vary from 50% to 80% depending on the given subset. The preliminary results found here point out the feasibility of such approach and can be used as a starting point for the pursuit of automatically generation of internal quality information about resources inside repositories.

KW - Artificial neural networks

KW - Learning object repositories

KW - Learning objects

KW - MERLOT

KW - Ranking mechanisms

KW - Ratings

UR - http://www.scopus.com/inward/record.url?scp=84893183219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893183219&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:84893183219

VL - 896

SP - 11

EP - 22

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

ER -