At a time of heightened interest in online learning and AI, there is a growing consensus that applications of AI in education have a transformational impact on the educational landscape.

The UQ AI in Education research group draws on insights from the learning sciences and exemplary techniques from the fields of human-computer interaction, human-centred AI and learning analytics to design, implement, validate and deliver technological solutions that contribute to the delivery of learner-centred, data-driven learning at scale. two example applications are discussed below.

Educational crowdsourcing to support personalisation

Adaptive educational systems (AESs) make use of data about students, learning processes, and learning products to adapt the level or type of instruction for each student. To effectively adapt to the learning needs of individual students, AESs rely on learner models that capture an abstract representation of a student’s ability level based on their performance and interactions with the system. The adaptive engine of an AES utilises information from the learner model to recommend items from a large repository of learning resources that best match the current learning needs of a student. These resources are commonly created by domain experts, which makes AESs expensive to develop and challenging to scale. 

RiPPLE is a UQ developed and supported AES that takes the crowdsourcing approach of partnering with students, also referred to as learnersourcing to create the resource repository. , To date, RiPPLE has been implemented in over 70 courses across a range of disciplines including Medicine, Pharmacy, Psychology, Education, Business, Computer Science and Biosciences. Over 13,000 students have engaged with RiPPLE. Students have created over 30,000 learning resources and over 250,000 peer evaluations rating the quality of these resources using RiPPLE and, over 1,000,000 interactions with personalised activities have been facilitated. 

Intelligent Learning Analytics Dashboards

Learning analytics dashboards commonly visualise data about students with the aim of assisting students and educators in understanding and making informed decisions about the learning process. To assist with making sense of complex and multi-dimensional data, many learning analytics systems and dashboards have relied significantly on AI algorithms based on predictive analytics. While predictive models have been successful in many domains, there is an increasing realisation of the inadequacies of using predictive models in decision-making tasks that affect individuals without human oversight.

To address this challenge, we have developed a learning analytics dashboard called Course Insights that employs a suite of state-of-the-art algorithms, from online analytics processing, data mining and process mining domains, to present an alternative human-in-the-loop AI method to enable educators to identify, explore and use appropriate interventions for subpopulations of students with the highest deviation in performance or learning process compared to the rest of the class. Course Insights has been well disseminated at UQ with 20% of all courses offered in Semester 2 of 2020 accessing it at least once during the semester.

Project members

Dr Hassan Khosravi

Associate Professor
Institute for Teaching and Learning Innovation
Affiliate Associate Professor of School of Education
School of Education

Professor Shazia Sadiq

School of Electrical Engineering and Computer Science

Associate Professor Gianluca Demartini

Associate Professor
School of Electrical Engineering and Computer Science