Promoting autonomy for language learning powered by data-driven methods and learner-centred design

This thesis explores innovative, data-driven methods to enhance autonomy in language learning. While it presents interdisciplinary work, the main focus is exploring the learner-centred design of three applications aiming to promote self-regulated behaviours among language learners. The following projects are presented: (1) H-Matrix offers a visualization tool for analyzing cross-linguistic features in large learner corpora. This tool supports users in identifying transfer effects and other patterns in learner data, aiding in developing targeted instructional strategies and promoting linguistic awareness for learners. (2) Card-it is a dynamic flashcard generator leveraging finite-state morphology to support the acquisition of Italian verb morphology. This application incorporates expert feedback and learner evaluations to refine its design, ensuring it effectively supports Italian verb conjugation training and morphological awareness. (3) LangEye captures the learner’s environment to create situated, personalized, context-aware vocabulary learning experiences. It leverages learner-curated curriculum and micro-learning opportunities, and it integrates generative AI to enable context personalization to enhance the relevance and retention of new vocabulary in the target language. Through user studies, including expert evaluations and learner interviews, this research indicates the efficacy of these applications in fostering autonomous, self-regulated language learning. It provides practical, data-driven solutions that empower learners to take control of their language acquisition journey. These findings contribute to technology-enhanced language learning (TELL) and human-computer interaction (HCI) for education.

Name thesis:degree_name

Doctor of Philosophy (PhD)

Discipline thesis:degree_discipline

Computer Science

Grantor

University of Ontario Institute of Technology

Year dc:date.issued

2024

Author dc:creator

• Shimabukuro, Mariana Akemi

Advisor dc:contributor.advisor

• Collins, Christopher

Language dc:language.iso

en

Handle dc:identifier.uri

https://hdl.handle.net/10155/1905

OAI identifier oai:identifier

oai:ontariotechu.scholaris.ca:10155/1905