arXiv subjects

Hassan Khosravi

Publications and source records attributed to Hassan Khosravi.

16 recordsLinked to original sources

arXiv2026

Making AI-Generated Feedback Matter: A Large-Scale Study of Feedback Workflows and Student Enactment

Feedback processes strongly influence student learning, yet their educational value depends on addressing two distinct challenges: providing high-quality, timely, and individualised feedback at scale, and supporting students to interpret, evaluate, and act on that feedback productively. Generative AI offers a credible means of addressing the provision challenge, but students' uptake of AI-generated feedback remains limited. We conducted a large-scale quasi-experimental sequential cohort study comparing three AI-mediated feedback workflows across 13,037 students and 51,296 student-authored resources. In Directed Feedback (n = 3,723), students received AI-generated feedback comments without structured support. In Self-Directed Feedback (n = 3,951), students could initiate optional AI-supported dialogue. In Enacted Feedback (n = 5,363), students were prompted to select feedback suggestions, evaluate their relevance, and engage in targeted AI-supported dialogue anchored to those selections. Enacted Feedback was associated with significantly higher uptake of AI-generated feedback, with an estimated probability of 26.2%, compared with 14.1% for Directed Feedback and 0.1% for Self-Directed Feedback. It was also associated with significantly higher self-assessment confidence and submitted-work quality than both comparison conditions. These findings suggest that the educational value of AI-generated feedback depends not only on the quality of feedback comments, but also on workflows that actively structure students' enactment of feedback literacy processes. The results have implications for the design of AI feedback systems that position learners as active participants in judgement, dialogue, and improvement rather than passive recipients of comments. Overall findings show that AI access alone is insufficient; purposeful workflow design is central to productive feedback use.

cs.AI↗

arXiv2026

Building AI Companions that Prioritise Learning over Performance

Large language models (LLMs) are rapidly transforming knowledge work by improving the quality and efficiency of tasks such as writing, coding, and data analysis. However, their growing use in education has exposed a learning-performance paradox: while they can enhance short-term task performance, they may also undermine genuine learning, including cognitive growth, knowledge transfer, and metacognitive development. This paper addresses the question of how artificial intelligence should be designed and used to support learning rather than merely improve immediate outputs. We introduce the concept of AI learning companions, defined as adaptive, pedagogically informed, LLM-powered agents designed for integration into learning environments. We propose a framework for their design built on three interrelated foundations: a pedagogical foundation focused on how students learn with AI, an adaptive foundation focused on how AI learns about students, and a responsible design foundation ensuring systems remain transparent, accountable, inclusive, and secure. The framework is illustrated through five case studies spanning diverse educational contexts, levels, and tool designs, revealing both the promise and current limitations of existing tools. We conclude that there is a necessary shift away from LLMs designed for task-oriented performance, and beyond simply prompting them to act as tutors, toward deliberately developed AI learning companions that are pedagogically sound, adapt to their learners, and foster durable understanding, metacognitive growth, and learner agency.

cs.HC↗

arXiv2025

Directive, Metacognitive or a Blend of Both? A Comparison of AI-Generated Feedback Types on Student Engagement, Confidence, and Outcomes

Feedback is one of the most powerful influences on student learning, with extensive research examining how best to implement it in educational settings. Increasingly, feedback is being generated by artificial intelligence (AI), offering scalable and adaptive responses. Two widely studied approaches are directive feedback, which gives explicit explanations and reduces cognitive load to speed up learning, and metacognitive feedback which prompts learners to reflect, track their progress, and develop self-regulated learning (SRL) skills. While both approaches have clear theoretical advantages, their comparative effects on engagement, confidence, and quality of work remain underexplored. This study presents a semester-long randomised controlled trial with 329 students in an introductory design and programming course using an adaptive educational platform. Participants were assigned to receive directive, metacognitive, or hybrid AI-generated feedback that blended elements of both directive and metacognitive feedback. Results showed that revision behaviour differed across feedback conditions, with Hybrid prompting the most revisions compared to Directive and Metacognitive. Confidence ratings were uniformly high, and resource quality outcomes were comparable across conditions. These findings highlight the promise of AI in delivering feedback that balances clarity with reflection. Hybrid approaches, in particular, show potential to combine actionable guidance for immediate improvement with opportunities for self-reflection and metacognitive growth.

cs.HC↗

arXiv2025

From Misunderstandings to Learning Opportunities: Leveraging Generative AI in Discussion Forums to Support Student Learning

In the contemporary educational landscape, particularly in large classroom settings, discussion forums have become a crucial tool for promoting interaction and addressing student queries. These forums foster a collaborative learning environment where students engage with both the teaching team and their peers. However, the sheer volume of content generated in these forums poses two significant interconnected challenges: How can we effectively identify common misunderstandings that arise in student discussions? And once identified, how can instructors use these insights to address them effectively? This paper explores the approach to integrating large language models (LLMs) and Retrieval-Augmented Generation (RAG) to tackle these challenges. We then demonstrate the approach Misunderstanding to Mastery (M2M) with authentic data from three computer science courses, involving 1355 students with 2878 unique posts, followed by an evaluation with five instructors teaching these courses. Results show that instructors found the approach promising and valuable for teaching, effectively identifying misunderstandings and generating actionable insights. Instructors highlighted the need for more fine-grained groupings, clearer metrics, validation of the created resources, and ethical considerations around data anonymity.

cs.HC↗

arXiv2024

Emotionally Enriched Feedback via Generative AI

This study investigates the impact of emotionally enriched AI feedback on student engagement and emotional responses in higher education. Leveraging the Control-Value Theory of Achievement Emotions, we conducted a randomized controlled experiment involving 425 participants where the experimental group received AI feedback enhanced with motivational elements, while the control group received neutral feedback. Our findings reveal that emotionally enriched feedback is perceived as more beneficial and helps reduce negative emotions, particularly anger, towards receiving feedback. However, it had no significant impact on the level of engagement with feedback or the quality of student work. These results suggest that incorporating emotional elements into AI-driven feedback can positively influence student perceptions and emotional well-being, without compromising work quality. Our study contributes to the growing body of research on AI in education by highlighting the importance of emotional considerations in educational technology design.

cs.HC↗

arXiv2024

How critically can an AI think? A framework for evaluating the quality of thinking of generative artificial intelligence

Generative AI such as those with large language models have created opportunities for innovative assessment design practices. Due to recent technological developments, there is a need to know the limits and capabilities of generative AI in terms of simulating cognitive skills. Assessing student critical thinking skills has been a feature of assessment for time immemorial, but the demands of digital assessment create unique challenges for equity, academic integrity and assessment authorship. Educators need a framework for determining their assessments vulnerability to generative AI to inform assessment design practices. This paper presents a framework that explores the capabilities of the LLM ChatGPT4 application, which is the current industry benchmark. This paper presents the Mapping of questions, AI vulnerability testing, Grading, Evaluation (MAGE) framework to methodically critique their assessments within their own disciplinary contexts. This critique will provide specific and targeted indications of their questions vulnerabilities in terms of the critical thinking skills. This can go on to form the basis of assessment design for their tasks.

cs.AI↗

arXiv2024

Large Language Models Meet User Interfaces: The Case of Provisioning Feedback

Incorporating Generative AI (GenAI) and Large Language Models (LLMs) in education can enhance teaching efficiency and enrich student learning. Current LLM usage involves conversational user interfaces (CUIs) for tasks like generating materials or providing feedback. However, this presents challenges including the need for educator expertise in AI and CUIs, ethical concerns with high-stakes decisions, and privacy risks. CUIs also struggle with complex tasks. To address these, we propose transitioning from CUIs to user-friendly applications leveraging LLMs via API calls. We present a framework for ethically incorporating GenAI into educational tools and demonstrate its application in our tool, Feedback Copilot, which provides personalized feedback on student assignments. Our evaluation shows the effectiveness of this approach, with implications for GenAI researchers, educators, and technologists. This work charts a course for the future of GenAI in education.

cs.HC↗

arXiv2023

Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.

cs.AI↗

arXiv2023

Can We Trust AI-Generated Educational Content? Comparative Analysis of Human and AI-Generated Learning Resources

As an increasing number of students move to online learning platforms that deliver personalized learning experiences, there is a great need for the production of high-quality educational content. Large language models (LLMs) appear to offer a promising solution to the rapid creation of learning materials at scale, reducing the burden on instructors. In this study, we investigated the potential for LLMs to produce learning resources in an introductory programming context, by comparing the quality of the resources generated by an LLM with those created by students as part of a learnersourcing activity. Using a blind evaluation, students rated the correctness and helpfulness of resources generated by AI and their peers, after both were initially provided with identical exemplars. Our results show that the quality of AI-generated resources, as perceived by students, is equivalent to the quality of resources generated by their peers. This suggests that AI-generated resources may serve as viable supplementary material in certain contexts. Resources generated by LLMs tend to closely mirror the given exemplars, whereas student-generated resources exhibit greater variety in terms of content length and specific syntax features used. The study highlights the need for further research exploring different types of learning resources and a broader range of subject areas, and understanding the long-term impact of AI-generated resources on learning outcomes.

cs.HC↗

arXiv2023

Learnersourcing in the Age of AI: Student, Educator and Machine Partnerships for Content Creation

Engaging students in creating novel content, also referred to as learnersourcing, is increasingly recognised as an effective approach to promoting higher-order learning, deeply engaging students with course material and developing large repositories of content suitable for personalized learning. Despite these benefits, some common concerns and criticisms are associated with learnersourcing (e.g., the quality of resources created by students, challenges in incentivising engagement and lack of availability of reliable learnersourcing systems), which have limited its adoption. This paper presents a framework that considers the existing learnersourcing literature, the latest insights from the learning sciences and advances in AI to offer promising future directions for developing learnersourcing systems. The framework is designed around important questions and human-AI partnerships relating to four key aspects: (1) creating novel content, (2) evaluating the quality of the created content, (3) utilising learnersourced contributions of students and (4) enabling instructors to support students in the learnersourcing process. We then present two comprehensive case studies that illustrate the application of the proposed framework in relation to two existing popular learnersourcing systems.

cs.HC↗

arXiv2019

A Multivariate Elo-based Learner Model for Adaptive Educational Systems

The Elo rating system has been recognised as an effective method for modelling students and items within adaptive educational systems. The existing Elo-based models have the limiting assumption that items are only tagged with a single concept and are mainly studied in the context of adaptive testing systems. In this paper, we introduce a multivariate Elo-based learner model that is suitable for the domains where learning items can be tagged with multiple concepts, and investigate its fit in the context of adaptive learning. To evaluate the model, we first compare the predictive performance of the proposed model against the standard Elo-based model using synthetic and public data sets. Our results from this study indicate that our proposed model has superior predictive performance compared to the standard Elo-based model, but the difference is rather small. We then investigate the fit of the proposed multivariate Elo-based model by integrating it into an adaptive learning system which incorporates the principles of open learner models (OLMs). The results from this study suggest that the availability of additional parameters derived from multivariate Elo-based models have two further advantages: guiding adaptive behaviour for the system and providing additional insight for students and instructors.

cs.CY↗

arXiv2019

RiPPLE: A Crowdsourced Adaptive Platform for Recommendation of Learning Activities

This paper presents a platform called RiPPLE (Recommendation in Personalised Peer-Learning Environments) that recommends personalized learning activities to students based on their knowledge state from a pool of crowdsourced learning activities that are generated by educators and the students themselves. RiPPLE integrates insights from crowdsourcing, learning sciences, and adaptive learning, aiming to narrow the gap between these large bodies of research while providing a practical platform-based implementation that instructors can easily use in their courses. This paper provides a design overview of RiPPLE, which can be employed as a standalone tool or embedded into any learning management system (LMS) or online platform that supports the Learning Tools Interoperability (LTI) standard. The platform has been evaluated based on a pilot in an introductory course with 453 students at The University of Queensland. Initial results suggest that the use of the \name platform led to measurable learning gains and that students perceived the platform as beneficially supporting their learning.

cs.HC↗

arXiv2019

Multilevel Visualisation of Topic Dependency Models for Assessment Design and Delivery: A Hypergraph Based Approach

The effective design and delivery of assessments in a wide variety of evolving educational environments remains a challenging problem. Proposals have included the use of learning dashboards, peer learning environments, and grading support systems; these embrace visualisations to summarise and communicate results. In an on-going project, the investigation of graph based visualisation models for assessment design and delivery has yielded promising results. Here, an alternative graph foundation, a two-weighted hypergraph, is considered to represent the assessment material (e.g., questions) and their explicit mapping to one or more learning objective topics. The visualisation approach considers the hypergraph as a collection of levels; the content of these levels can be customized and presented according to user preferences. A case study on generating hypergraph models using commonly available assessment data and a flexible visualisation approach using historical data from an introductory programming course is presented

cs.HC↗

arXiv2018

Recommendation in Personalised Peer-Learning Environments

Recommendation in Personalised Peer Learning Environments (RiPPLE) is an adaptive, crowdsourced, web-based, student-facing, open-source platform that employs exemplary techniques from the fields of machine learning, crowdsourcing, learning analytics and recommender systems to provide personalised content and learning support at scale. RiPPLE presents students with a repository of tagged multiple-choice questions and provides instant feedback in response to student answers. The repository of the questions is created in partnership with the students through the use of crowdsourcing. RiPPLE uses students responses to the questions to approximate their knowledge states. Based on their knowledge state and learning needs, each student is recommended a set of personalised questions. For students that are interested in providing learning support, seeking learning support or finding study partners, RiPPLE recommends peer learning sessions based on their availability, knowledge state and preferences. This paper describes the RiPPLE interface and an implementation of that interface that has been built at the University of Queensland. The RiPPLE platform and a reference implementation are released as an open-source package under the Apache 2.0 license via GitHub.

cs.CY↗

arXiv2017

RiPLE: Recommendation in Peer-Learning Environments Based on Knowledge Gaps and Interests

Various forms of Peer-Learning Environments are increasingly being used in post-secondary education, often to help build repositories of student generated learning objects. However, large classes can result in an extensive repository, which can make it more challenging for students to search for suitable objects that both reflect their interests and address their knowledge gaps. Recommender Systems for Technology Enhanced Learning (RecSysTEL) offer a potential solution to this problem by providing sophisticated filtering techniques to help students to find the resources that they need in a timely manner. Here, a new RecSysTEL for Recommendation in Peer-Learning Environments (RiPLE) is presented. The approach uses a collaborative filtering algorithm based upon matrix factorization to create personalized recommendations for individual students that address their interests and their current knowledge gaps. The approach is validated using both synthetic and real data sets. The results are promising, indicating RiPLE is able to provide sensible personalized recommendations for both regular and cold-start users under reasonable assumptions about parameters and user behavior.

cs.CY↗

arXiv2009

Learning Class-Level Bayes Nets for Relational Data

Many databases store data in relational format, with different types of entities and information about links between the entities. The field of statistical-relational learning (SRL) has developed a number of new statistical models for such data. In this paper we focus on learning class-level or first-order dependencies, which model the general database statistics over attributes of linked objects and links (e.g., the percentage of A grades given in computer science classes). Class-level statistical relationships are important in themselves, and they support applications like policy making, strategic planning, and query optimization. Most current SRL methods find class-level dependencies, but their main task is to support instance-level predictions about the attributes or links of specific entities. We focus only on class-level prediction, and describe algorithms for learning class-level models that are orders of magnitude faster for this task. Our algorithms learn Bayes nets with relational structure, leveraging the efficiency of single-table nonrelational Bayes net learners. An evaluation of our methods on three data sets shows that they are computationally feasible for realistic table sizes, and that the learned structures represent the statistical information in the databases well. After learning compiles the database statistics into a Bayes net, querying these statistics via Bayes net inference is faster than with SQL queries, and does not depend on the size of the database.

cs.LG↗