Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence

This paper proposes the adoption of a deep learning method to automate the categorisation of online discussion messages according to the phases of cognitive presence, a fundamental construct from the widely used Community of Inquiry (CoI) framework of online learning. We investigated not only the pe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuanyuan Hu, Rafael Ferreira Mello, Dragan Gašević
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Cognitive presence Deep learning Explainable artificial intelligence Online discussion Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/5aed43eca65b4b17ad1e5f2cb13c50da
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5aed43eca65b4b17ad1e5f2cb13c50da
record_format	dspace
spelling	oai:doaj.org-article:5aed43eca65b4b17ad1e5f2cb13c50da2021-11-04T04:43:38ZAutomatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence2666-920X10.1016/j.caeai.2021.100037https://doaj.org/article/5aed43eca65b4b17ad1e5f2cb13c50da2021-01-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666920X2100031Xhttps://doaj.org/toc/2666-920XThis paper proposes the adoption of a deep learning method to automate the categorisation of online discussion messages according to the phases of cognitive presence, a fundamental construct from the widely used Community of Inquiry (CoI) framework of online learning. We investigated not only the performance of a deep learning classifier but also its generalisability and interpretability, using explainable artificial intelligence algorithms. In the study, we compared a Convolution Neural Network (CNN) model with the previous approaches reported on the literature based on random forest classifiers and linguistics features of psychological processes and cohesion. The CNN classifier trained and tested on the individual data set reached results up to Cohen's κ of 0.528, demonstrating a similar performance to those of the random forest classifiers. Also, the generalisability outcomes of the CNN classifiers across two disciplinary courses were similar to the results of the random forest approach. Finally, the visualisations of explainable artificial intelligence provide novel insights into identifying the phases of cognitive presence by word-level relevant indicators, as a complement to the feature importance analysis from the random forest. Thus, we envisage combining the deep learning method and the conventional machine learning algorithms (e.g. random forest) as complementary approaches to classify the phases of cognitive presence.Yuanyuan HuRafael Ferreira MelloDragan GaševićElsevierarticleCognitive presenceDeep learningExplainable artificial intelligenceOnline discussionElectronic computers. Computer scienceQA75.5-76.95ENComputers and Education: Artificial Intelligence, Vol 2, Iss , Pp 100037- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Cognitive presence Deep learning Explainable artificial intelligence Online discussion Electronic computers. Computer science QA75.5-76.95
spellingShingle	Cognitive presence Deep learning Explainable artificial intelligence Online discussion Electronic computers. Computer science QA75.5-76.95 Yuanyuan Hu Rafael Ferreira Mello Dragan Gašević Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence
description	This paper proposes the adoption of a deep learning method to automate the categorisation of online discussion messages according to the phases of cognitive presence, a fundamental construct from the widely used Community of Inquiry (CoI) framework of online learning. We investigated not only the performance of a deep learning classifier but also its generalisability and interpretability, using explainable artificial intelligence algorithms. In the study, we compared a Convolution Neural Network (CNN) model with the previous approaches reported on the literature based on random forest classifiers and linguistics features of psychological processes and cohesion. The CNN classifier trained and tested on the individual data set reached results up to Cohen's κ of 0.528, demonstrating a similar performance to those of the random forest classifiers. Also, the generalisability outcomes of the CNN classifiers across two disciplinary courses were similar to the results of the random forest approach. Finally, the visualisations of explainable artificial intelligence provide novel insights into identifying the phases of cognitive presence by word-level relevant indicators, as a complement to the feature importance analysis from the random forest. Thus, we envisage combining the deep learning method and the conventional machine learning algorithms (e.g. random forest) as complementary approaches to classify the phases of cognitive presence.
format	article
author	Yuanyuan Hu Rafael Ferreira Mello Dragan Gašević
author_facet	Yuanyuan Hu Rafael Ferreira Mello Dragan Gašević
author_sort	Yuanyuan Hu
title	Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence
title_short	Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence
title_full	Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence
title_fullStr	Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence
title_full_unstemmed	Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence
title_sort	automatic analysis of cognitive presence in online discussions: an approach using deep learning and explainable artificial intelligence
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/5aed43eca65b4b17ad1e5f2cb13c50da
work_keys_str_mv	AT yuanyuanhu automaticanalysisofcognitivepresenceinonlinediscussionsanapproachusingdeeplearningandexplainableartificialintelligence AT rafaelferreiramello automaticanalysisofcognitivepresenceinonlinediscussionsanapproachusingdeeplearningandexplainableartificialintelligence AT dragangasevic automaticanalysisofcognitivepresenceinonlinediscussionsanapproachusingdeeplearningandexplainableartificialintelligence
_version_	1718445212134539264

Automatic analysis of cognitive presence in online discussions: An approach using deep learning and explainable artificial intelligence

Ejemplares similares