Learner-centred feedback
Operationalising Future Impact, Sensemaking, and Agency in feedback: actionable guidance, explanation, learner agency, and supportive interaction.
I study how AI can help teachers give students feedback they can act on, combining LLM evaluation, educational NLP, and learning analytics on authentic assessment data.
I am a PhD candidate in Information Technology (Learning Analytics) at Monash University's Centre for Learning Analytics, submitting my thesis in December 2026, and a Teaching Associate in Monash's Faculty of Information Technology. I am also a Lecturer (Assistant Professor) at Universitas Teknokrat Indonesia. I hold a Bachelor's and a Master's in Mathematics from Universitas Lampung.
- 5
- articles in leading AI-in-education journals, 2024–2026
- 3
- as first author
- 1,000+
- Google Scholar citations
- Dec 2026
- PhD thesis submission
Research focus
Generative AI & LLM evaluation
Designing and evaluating LLM feedback workflows across prompting conditions, and comparing AI-generated with teacher feedback on pedagogical and linguistic measures.
Educational NLP & datasets
Curating and annotating authentic feedback datasets; multilabel classification with BERT-based models and careful validation.
Learning analytics & outcomes
Linking feedback, educator–AI interaction, and student revision to subsequent academic performance.
Methods & tools: Python · R · SQL · BERT · scikit-learn · PyTorch · LLM APIs & prompt design · statistical modelling · qualitative thematic analysis · dataset annotation
Doctoral research
Five connected studies, from mapping feedback to automating its analysis to how teachers and students use it.
- 1
Mapping learner-centred feedback
Analysed authentic higher-education feedback, its alignment with learner-centred components, and patterns across student groups.
Published · Computers & Education, 2025 - 2
Automating feedback analysis
Machine learning and NLP to classify learner-centred feedback; BERT-based classifiers reached Cohen's κ up to 0.956 and F1 up to 0.998. Implemented in PolyFeed.
Published · Computers and Education: AI, 2024 - 3
Human and LLM-generated feedback
Compared 5,156 human- and LLM-generated feedback texts on 1,289 student proposals, across prompting strategies, on pedagogical and linguistic features.
Under review - 4
Teacher–AI collaboration
How educators use, revise, and trust AI-supported feedback in PolyFeed, including ethics and usability.
Published · Assessment & Evaluation in Higher Education, 2026 - 5
Feedback and student outcomes
Linked learner-centred feedback components to revision actions and subsequent performance for 1,946 students across three semesters.
In preparation
PolyFeed, an AI-supported feedback analytics system, includes the classification model I built in Study 2. Meet the PolyFeed team.
Selected publications
- Enhancing learner-centered feedback with AI: Teachers' practices and perceptionsAldino, A. A., Maheshi, B., Li, Y., Zhou, Y., Tsai, Y.-S., Gašević, D., & Chen, G.Assessment & Evaluation in Higher Education, 51(5), 892–910 · 2026
- Analytics of learner-centered feedback: A large-scale case study in higher educationAldino, A. A., Tsai, Y.-S., Gupte, S., Henderson, M., Nath, D., Gašević, D., & Chen, G.Computers & Education, 237, 105360 · 2025
- Evaluating the capability of large language models in characterising relational feedback: A comparative analysis of prompting strategiesDai, W., Cheng, Y., Aldino, A. A., Tsai, Y.-S., Gašević, D., & Chen, G.Computers and Education: Artificial Intelligence, 8, 100427 · 2025
- Enhancing feedback quality at scale: Leveraging machine learning for learner-centered feedbackAldino, A. A., Tsai, Y.-S., Mello, R. F., Gašević, D., & Chen, G.Computers and Education: Artificial Intelligence, 7, 100332 · 2024
- Assessing the proficiency of large language models in automatic feedback generation: An evaluation studyDai, W., Tsai, Y.-S., Lin, J., Aldino, A. A., Jin, H., Li, T., Gašević, D., & Chen, G.Computers and Education: Artificial Intelligence, 7, 100299 · 2024
Full list on Google Scholar.
Research agenda
From analysing feedback to improving it, with AI and teachers together.
Human–AI co-authored feedback
Design and test workflows where teachers and LLMs write feedback together, and measure whether it leads to better student revisions and learning than either alone.
Trustworthy evaluation of AI feedback
Evaluation frameworks that combine pedagogical quality, reliability, and fairness, so institutions can adopt AI feedback tools with evidence.
Feedback uptake at scale
Trace how students act on feedback over time across courses and institutions, moving towards longitudinal and quasi-experimental designs.
Teaching & appointments
- 2023 – present
Teaching Associate · Monash University
Postgraduate data science in the Faculty of Information Technology, including FIT5145: tutorials, consultations, assessment, and feedback.
- 2019 – present
Lecturer (Assistant Professor) · Universitas Teknokrat Indonesia
Undergraduate data mining, statistics, data visualisation, data warehousing, and data science; curriculum design and thesis supervision.
- 2013 – 2015
Assistant Lecturer · Universitas Lampung
Supported undergraduate and graduate teaching in information technology and programming.
Education
PhD, Information Technology (Learning Analytics)
Monash University · 2023–2026 · BPI scholarship
Master of Mathematics
Universitas Lampung · 2019
Bachelor of Mathematics
Universitas Lampung · 2015
Service & membership
Peer reviewer, 2024–2026
Computers & Education: AI · Teaching and Teacher Education · Education and Information Technologies · Assessment & Evaluation in Higher Education · Heliyon · Cogent Business & Management
Member, Society for Learning Analytics Research (SoLAR), 2024–present
Contact
I am open to postdoctoral positions from 2027 in AI in education, learning analytics, and educational NLP, and welcome conversations with researchers and educators.