From the Discovery of Students Access Patterns in E-learning Including Web 2.0 Resources to the Prediction and Enhancement of Students Outcome

Pérez‐Marín, Diana; Velázquez‐Iturbide, J. Ángel

doi:10.5772/8802

Cited by 2 publications

(3 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The purpose of their system was to measure the effect of blended e-learning. Similarly, the authors of [5] measure patterns in a Web 2.0 learning environment.…”

Section: Context and Related Workmentioning

confidence: 98%

See 1 more Smart Citation

TinCan2PROV

Nies

Salliau

Verborgh

et al. 2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

A popular way to log learning processes is by using the Experience API (abbreviated as xAPI), also referred to as Tin Can. While Tin Can is great for developers who need to log learning experiences in their applications, it is more challenging for data processors to interconnect and analyze the resulting data. An interoperable data model is missing to raise Tin Can to its full potential. We argue that in essence, these learning process logs are provenance. Therefore, the W3C PROV model can provide the much-needed interoperability. In this paper, we introduce a method to expose PROV using Tin Can statements. To achieve this, we made the following contributions: (1) a formal ontology of the xAPI vocabulary, (2) a context document to interpret xAPI statements as JSON-LD, (3) a mapping to convert xAPI JSON-LD statements into PROV, and (4) a tool implementing this mapping. We preliminarily evaluate the approach by converting 20 xAPI statements taken from the public Tin Can Learning Record Store to valid PROV. Where the conversion succeeded, it did so without loss of valid information, therefore suggesting that the conversion process is reversible, as long as the original JSON is valid.

show abstract

“…The purpose of their system was to measure the effect of blended e-learning. Similarly, the authors of [5] measure patterns in a Web 2.0 learning environment.…”

Section: Context and Related Workmentioning

confidence: 98%

“…Others have created their own serializations, such as PROV-JSON [7] and SVG. 5 Prefixes omitted for clarity. …”

Section: Serializationmentioning

confidence: 99%

TinCan2PROV

Nies

Salliau

Verborgh

et al. 2015

Proceedings of the 24th International Conference on World Wide Web

View full text Add to dashboard Cite

show abstract

“…Learning Management Systems (LMSs) frame a digital learning environment where the user’s learning behavior and it’s evaluation need to be efficiently amended 11 . LMSs (e.g., Moodle, https://moodle.org/ ) are actually embedded within OLE, which usually offer quick access, huge data management and a variety of Web-based tools 12 , 13 .…”

Section: Introductionmentioning

confidence: 99%

DeepLMS: a deep learning predictive model for supporting online learning in the Covid-19 era

Dias

Hadjileontiadou

Diniz

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Coronavirus (Covid-19) pandemic has imposed a complete shut-down of face-to-face teaching to universities and schools, forcing a crash course for online learning plans and technology for students and faculty. In the midst of this unprecedented crisis, video conferencing platforms (e.g., Zoom, WebEx, MS Teams) and learning management systems (LMSs), like Moodle, Blackboard and Google Classroom, are being adopted and heavily used as online learning environments (OLEs). However, as such media solely provide the platform for e-interaction, effective methods that can be used to predict the learner’s behavior in the OLEs, which should be available as supportive tools to educators and metacognitive triggers to learners. Here we show, for the first time, that Deep Learning techniques can be used to handle LMS users’ interaction data and form a novel predictive model, namely DeepLMS, that can forecast the quality of interaction (QoI) with LMS. Using Long Short-Term Memory (LSTM) networks, DeepLMS results in average testing Root Mean Square Error (RMSE) $$<0.009$$ < 0.009 , and average correlation coefficient between ground truth and predicted QoI values $$r\ge 0.97$$ r ≥ 0.97 $$(p<0.05)$$ ( p < 0.05 ) , when tested on QoI data from one database pre- and two ones during-Covid-19 pandemic. DeepLMS personalized QoI forecasting scaffolds user’s online learning engagement and provides educators with an evaluation path, additionally to the content-related assessment, enriching the overall view on the learners’ motivation and participation in the learning process.

show abstract

From the Discovery of Students Access Patterns in E-learning Including Web 2.0 Resources to the Prediction and Enhancement of Students Outcome

Abstract: Finally, conclusions about using this new module developed for Moodle and the importance of prediction of students' outcome to enhance teaching and learning.

Cited by 2 publications

References 12 publications

TinCan2PROV

TinCan2PROV

DeepLMS: a deep learning predictive model for supporting online learning in the Covid-19 era

Contact Info

Product

Resources

About