Personalized, Open Educational Resource (OER) Recommender for Continuous Skill Improvement

Contributors

OER recommendation:

  • Mohammadreza Tavakoli (TIB)

Labour Market Intelligence (LMI):

  • Jarno Vrolijk (UvA)
  • Alan Berg (UvA)

Principle Investigators:

  • Gábor Kismihók (TIB)
  • Stefan Mol (UvA)

Aim

Exploiting LMI together with OER recommendations with the explicit goal of scaffolding learners’ study activities towards their career

Approach:

  • Modelling personal needs and characteristics in the light of changing nature of occupations.
  • Personal skill goals define individual learning objectives.
  • Dynamic, personalised curriculum generation, on the basis of learning objectives.
  • Open and transparent learning content recommendation.
  • Implementing continuous monitoring and feedback mechanisms through Learning Analytics (LA).
  • Modelling personal needs and characteristics in the light of changing nature of occupations.
  • Personal skill goals define individual learning objectives.
  • Dynamic, personalised curriculum generation, on the basis of learning objectives.
  • Open and transparent learning content recommendation.
  • Implementing continuous monitoring and feedback mechanisms through Learning Analytics (LA).

Status

First prototype, with the following functions:

  • Skills and occupations are implemented in the area of Data Science with an initial, limited, dataset
  • We tested the following OER content repositories for content accessibility from our platform:
    • Skillscommons
    • Wisc-Online
    • Youtube
    • TIB-AV portal
  • The initial skill – job matching algorithm is implemented
  • The initial skill – OER content matching algorithm is implemented
  • Two expert based validation studies have been successfully completed: 1, with Skillscommons and Wisc-Online on general OER content and 2, with Youtube and TIB AV-Portal on video content
  • Global labour market data was acquired from Burning Glass Technologies for the research
  • Currently we proceed towards larger validation studies with learners (researchers) in data science (conducting a user requirement analysis):
    • 1, Local study at the University of Amsterdam and
    • 2, Global Study with the Marie Curie Alumni Association
  • Based on the user requirements analysis we will come up with a service implementation strategy, a focussed validation strategy, update the content portfolio, and design a proper user interface

Screenshots

Setting a skill target


Receiving recommendations for a skill target:


Setting a job target


Getting recommendations for skills relevant to that job

Feedback