Quality Prediction of Open Educational Resources A Metadata-based Approach

Tavakoli, Mohammadreza; Elias, Mirette; Kismihók, Gábor; Auer, Sören

doi:10.48550/arxiv.2005.10542

“…completeness and consistency of metadata [14], provenance, and accuracy of metadata [15]) in order to assess the quality of OER metadata. To support this, [8] showed that a metadata scoring method can be used to define a model to predict OER quality.…”

Section: A Oer Quality Assessmentmentioning

confidence: 99%

“…2) Quality Prediction Based on Metadata: Previously we proposed a metadata scoring model based on 8,887 crawled OERs from Skill Commons [8] 8 . This model divides OERs in two groups: OERs with Manual Quality Control, and OERs Without Quality Control.…”

Section: A Oer Quality Predictormentioning

confidence: 99%

“…This means, that the more an OER passes quality controls, the higher the probability of containing high-quality metadata is. However, due to the rapidly growing amount of OERs, manual quality control is getting more and more impossible [8]. As a consequence, we built a model that predicts OER quality based on their metadata with F1-score of 94.6%.…”

Section: A Oer Quality Predictormentioning

confidence: 99%

“…Previous efforts to build educational search and recommender systems using the rapidly growing amount of OERs [5]- [7] revealed the lack of high-quality OER metadata, and quality control [8]. These issues seriously limit the deployment of high-quality OER search and recommendation services [9], [10].…”

Section: Introductionmentioning

confidence: 99%

“…In this paper, therefore, we showcase our attempt to extend our personalised, labour market information based OER recommender [4] with OER quality prediction models [11] and enhanced metadata scoring [8]. Furthermore, we show the integration process of 7 different OER repositories, and our latest learner dashboard prototype focused on Data Science related jobs.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

OER Recommendations to Support Career Development

Tavakoli¹,

Faraji²,

Mol³

et al. 2020

Preprint

Self Cite

0

View full text Add to dashboard Cite

This Work in Progress Research paper departs from the recent, turbulent changes in global societies, forcing many citizens to re-skill themselves to (re)gain employment. Learners therefore need to be equipped with skills to be autonomous and strategic about their own skill development. Subsequently, highquality, on-line, personalized educational content and services are also essential to serve this high demand for learning content. Open Educational Resources (OERs) have high potential to contribute to the mitigation of these problems, as they are available in a wide range of learning and occupational contexts globally. However, their applicability has been limited, due to low metadata quality and complex quality control. These issues resulted in a lack of personalised OER functions, like recommendation and search. Therefore, we suggest a novel, personalised OER recommendation method to match skill development targets with open learning content. This is done by: 1) using an OER quality prediction model based on metadata, OER properties, and content; 2) supporting learners to set individual skill targets based on actual labour market information, and 3) building a personalized OER recommender to help learners to master their skill targets. Accordingly, we built a prototype focusing on Data Science related jobs, and evaluated this prototype with 23 data scientists in different expertise levels. Pilot participants used our prototype for at least 30 minutes and commented on each of the recommended OERs. As a result, more than 400 recommendations were generated and 80.9% of the recommendations were reported as useful.

show abstract

OER Recommendations to Support Career Development

Tavakoli

¹

,

Faraji

²

,

Mol

³

et al. 2020

2020 IEEE Frontiers in Education Conference (FIE)

Self Cite

View full text Add to dashboard Cite

This Work in Progress Research paper departs from the recent, turbulent changes in global societies, forcing many citizens to re-skill themselves to (re)gain employment. Learners therefore need to be equipped with skills to be autonomous and strategic about their own skill development. Subsequently, highquality, on-line, personalized educational content and services are also essential to serve this high demand for learning content. Open Educational Resources (OERs) have high potential to contribute to the mitigation of these problems, as they are available in a wide range of learning and occupational contexts globally. However, their applicability has been limited, due to low metadata quality and complex quality control. These issues resulted in a lack of personalised OER functions, like recommendation and search. Therefore, we suggest a novel, personalised OER recommendation method to match skill development targets with open learning content. This is done by: 1) using an OER quality prediction model based on metadata, OER properties, and content; 2) supporting learners to set individual skill targets based on actual labour market information, and 3) building a personalized OER recommender to help learners to master their skill targets. Accordingly, we built a prototype focusing on Data Science related jobs, and evaluated this prototype with 23 data scientists in different expertise levels. Pilot participants used our prototype for at least 30 minutes and commented on each of the recommended OERs. As a result, more than 400 recommendations were generated and 80.9% of the recommendations were reported as useful.

show abstract

Extracting Topics from Open Educational Resources

Molavi¹,

Tavakoli²,

Kismihók³

2020

Preprint

Self Cite

0

View full text Add to dashboard Cite

In recent years, Open Educational Resources (OERs) were earmarked as critical when mitigating the increasing need for education globally. Obviously, OERs have high-potential to satisfy learners in many different circumstances, as they are available in a wide range of contexts. However, the low-quality of OER metadata, in general, is one of the main reasons behind the lack of personalised services such as search and recommendation. As a result, the applicability of OERs remains limited. Nevertheless, OER metadata about covered topics (subjects) is essentially required by learners to build effective learning pathways towards their individual learning objectives. Therefore, in this paper, we report on a work in progress project proposing an OER topic extraction approach, applying text mining techniques, to generate high-quality OER metadata about topic distribution. This is done by: 1) collecting 123 lectures from Coursera and Khan Academy in the area of data science related skills, 2) applying Latent Dirichlet Allocation (LDA) on the collected resources in order to extract existing topics related to these skills, and 3) defining topic distributions covered by a particular OER. To evaluate our model, we used the data-set of educational resources from Youtube, and compared our topic distribution results with their manually defined target topics with the help of 3 experts in the area of data science. As a result, our model extracted topics with 79% of F1-score.

show abstract

Quality Prediction of Open Educational Resources A Metadata-based Approach

Cited by 3 publications

References 11 publications

OER Recommendations to Support Career Development

OER Recommendations to Support Career Development

OER Recommendations to Support Career Development

Extracting Topics from Open Educational Resources

Contact Info

Product

Resources

About