What question did this study set out to answer?

To continuously predict student academic performance and identify at-risk learners in virtual learning environments by modeling both static biographical profiles and dynamic sequential behavior.

October 9, 2020InformationOpen Access

Online At-Risk Student Identification using RNN-GRU Joint Neural Networks

View Full Paper

Ask AI

Bookmark

To continuously predict student academic performance and identify at-risk learners in virtual learning environments by modeling both static biographical profiles and dynamic sequential behavior.
Evaluated simple recurrent neural networks (RNN), gated recurrent units (GRU), and long short-term memory (LSTM) architectures on the Open University Learning Analytics Dataset (OULAD).
Engineered an RNN-GRU joint neural network integrating a data completion mechanism to reconstruct missing stream data and process static background inputs alongside sequential logs.
Simpler sequential models (GRU and simple RNN) achieved superior performance compared to the more complex LSTM architecture.
The proposed joint RNN-GRU neural network attained greater than 80% prediction accuracy for at-risk students by the conclusion of the semester.

Authors

YHYanbai HeBeijing Normal University RCRui ChenHarbin Engineering University XLXinya LiJinan University

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

Predictive modeling study demonstrates over 80% accuracy in identifying at-risk learners in virtual classrooms, highlighting the efficacy of joint recurrent neural networks.

Cite This Study

He et al. (2020) studied this question.

synapsesocial.com/papers/69df0f8dd85e58e37b7a110a https://doi.org/10.3390/info11100474

View Full Paper

Ask AI

Bookmark

Implication

Predictive modeling study demonstrates over 80% accuracy in identifying at-risk learners in virtual classrooms, highlighting the efficacy of joint recurrent neural networks.

Online At-Risk Student Identification using RNN-GRU Joint Neural Networks

Key Points

Discussion

Implication

Cite This Study

Online At-Risk Student Identification using RNN-GRU Joint Neural Networks

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider