Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs

The quality assurance of MOOCs focuses on improving their pedagogical quality. However, the tools that allow reflection on and assistance regarding the pedagogical aspects of MOOCs are limited. The pedagogical classification of MOOCs is a difficult task, given the variability of MOOCs' content,...

Full description

Bibliographic Details
Main Authors: Hanane Sebbaq, Nour-eddine El Faddouli
Format: Article
Language:English
Published: Athabasca University Press 2022-05-01
Series:International Review of Research in Open and Distributed Learning
Subjects:
Online Access:http://www.irrodl.org/index.php/irrodl/article/view/6023
_version_ 1817985571654467584
author Hanane Sebbaq
Nour-eddine El Faddouli
author_facet Hanane Sebbaq
Nour-eddine El Faddouli
author_sort Hanane Sebbaq
collection DOAJ
description The quality assurance of MOOCs focuses on improving their pedagogical quality. However, the tools that allow reflection on and assistance regarding the pedagogical aspects of MOOCs are limited. The pedagogical classification of MOOCs is a difficult task, given the variability of MOOCs' content, structure, and designs. Pedagogical researchers have adopted several approaches to examine these variations and identify the pedagogical models of MOOCs, but these approaches are manual and operate on a small scale. Furthermore, MOOCs do not contain any metadata on their pedagogical aspects. Our objective in this research work was the automatic and large-scale classification of MOOCs based on their learning objectives and Bloom’s taxonomy. However, the main challenge of our work was the lack of annotated data. We created a dataset of 2,394 learning objectives. Due to the limited size of our dataset, we adopted transfer learning via bidirectional encoder representations from Transformers (BERT). The contributions of our approach are twofold. First, we automated the pedagogical annotation of MOOCs on a large scale and based on the cognitive levels of Bloom’s taxonomy. Second, we fine-tuned BERT via different architectures. In addition to applying a simple softmax classifier, we chose prevalent neural networks long short-term memory (LSTM) and Bi-directional long short-term memory (Bi-LSTM). The results of our experiments showed, on the one hand, that choosing a more complex classifier does not boost the performance of classification. On the other hand, using a model based on dense layers upon BERT in combination with dropout and the rectified linear unit (ReLU) activation function enabled us to reach the highest accuracy value.
first_indexed 2024-04-13T23:58:53Z
format Article
id doaj.art-f70a9dfe69bd41b7b8ad6c0a0b01d936
institution Directory Open Access Journal
issn 1492-3831
language English
last_indexed 2024-04-13T23:58:53Z
publishDate 2022-05-01
publisher Athabasca University Press
record_format Article
series International Review of Research in Open and Distributed Learning
spelling doaj.art-f70a9dfe69bd41b7b8ad6c0a0b01d9362022-12-22T02:23:46ZengAthabasca University PressInternational Review of Research in Open and Distributed Learning1492-38312022-05-0123210.19173/irrodl.v23i2.6023Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCsHanane Sebbaq0Nour-eddine El Faddouli 1RIME Team, MASI Laboratory, E3S Research center Mohammadia School of Engineers, Mohammed V University, Rabat, MoroccoRIME Team, MASI Laboratory, E3S Research center Mohammadia School of Engineers, Mohammed V University, Rabat, MoroccoThe quality assurance of MOOCs focuses on improving their pedagogical quality. However, the tools that allow reflection on and assistance regarding the pedagogical aspects of MOOCs are limited. The pedagogical classification of MOOCs is a difficult task, given the variability of MOOCs' content, structure, and designs. Pedagogical researchers have adopted several approaches to examine these variations and identify the pedagogical models of MOOCs, but these approaches are manual and operate on a small scale. Furthermore, MOOCs do not contain any metadata on their pedagogical aspects. Our objective in this research work was the automatic and large-scale classification of MOOCs based on their learning objectives and Bloom’s taxonomy. However, the main challenge of our work was the lack of annotated data. We created a dataset of 2,394 learning objectives. Due to the limited size of our dataset, we adopted transfer learning via bidirectional encoder representations from Transformers (BERT). The contributions of our approach are twofold. First, we automated the pedagogical annotation of MOOCs on a large scale and based on the cognitive levels of Bloom’s taxonomy. Second, we fine-tuned BERT via different architectures. In addition to applying a simple softmax classifier, we chose prevalent neural networks long short-term memory (LSTM) and Bi-directional long short-term memory (Bi-LSTM). The results of our experiments showed, on the one hand, that choosing a more complex classifier does not boost the performance of classification. On the other hand, using a model based on dense layers upon BERT in combination with dropout and the rectified linear unit (ReLU) activation function enabled us to reach the highest accuracy value. http://www.irrodl.org/index.php/irrodl/article/view/6023cognitive MOOC classificationBERTLSTMtransfer learning
spellingShingle Hanane Sebbaq
Nour-eddine El Faddouli
Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs
International Review of Research in Open and Distributed Learning
cognitive MOOC classification
BERT
LSTM
transfer learning
title Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs
title_full Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs
title_fullStr Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs
title_full_unstemmed Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs
title_short Fine-tuned BERT Model for Large Scale and Cognitive Classification of MOOCs
title_sort fine tuned bert model for large scale and cognitive classification of moocs
topic cognitive MOOC classification
BERT
LSTM
transfer learning
url http://www.irrodl.org/index.php/irrodl/article/view/6023
work_keys_str_mv AT hananesebbaq finetunedbertmodelforlargescaleandcognitiveclassificationofmoocs
AT noureddineelfaddouli finetunedbertmodelforlargescaleandcognitiveclassificationofmoocs