Advancing Learning Analytics: Detect and Predict Confusion in Learners Through AI

Samani, Chaitali J.

Advancing Learning Analytics: Detect and Predict Confusion in Learners Through AI

Samani, Chaitali J.

Permalink

Publication Type:: Thesis
Issue Date:: 2025

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (2.49 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Samani, Chaitali J.
dc.date.accessioned	2026-02-10T01:25:11Z
dc.date.available	2026-02-10T01:25:11Z
dc.date.issued	2025
dc.identifier.uri	http://hdl.handle.net/10453/193134
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	As digital education platforms continue to evolve, understanding learner engagement and emotional states has become critical for improving academic outcomes and reducing dropout rates. This thesis explores the detection and prediction of confusion—an essential epistemic emotion that influences positive and negative learning experiences. Using clickstream data from online platforms, this study develops predictive models with AI, specifically focusing on confusion in online learning. The methodology integrates clustering, time series analysis, and advanced AI algorithms, including Generative AI, to detect confusion patterns and provide real-time interventions. Results indicate that predictive modelling based on clickstream data can effectively identify confusion and its influence on learner engagement. This research offers a framework for improving learning analytics, contributing to personalised learning experiences and broader educational interventions.	en_US.UTF-8
dc.format	Thesis (MAnalytics)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/193134/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2025 Chaitali Samani
dc.rights	au.edu.uts.lib/cph
dc.title	Advancing Learning Analytics: Detect and Predict Confusion in Learners Through AI	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

As digital education platforms continue to evolve, understanding learner engagement and emotional states has become critical for improving academic outcomes and reducing dropout rates. This thesis explores the detection and prediction of confusion—an essential epistemic emotion that influences positive and negative learning experiences. Using clickstream data from online platforms, this study develops predictive models with AI, specifically focusing on confusion in online learning. The methodology integrates clustering, time series analysis, and advanced AI algorithms, including Generative AI, to detect confusion patterns and provide real-time interventions. Results indicate that predictive modelling based on clickstream data can effectively identify confusion and its influence on learner engagement. This research offers a framework for improving learning analytics, contributing to personalised learning experiences and broader educational interventions.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/193134