An AI maths tutor developed by Adelaide University researchers is now available for teachers to try, offering a working example of what artificial intelligence can currently do in the classroom using simple prompts.
The tool accompanies new research published in npj Science of Learning, which explores how AI systems might detect signs of anxiety or disengagement during learning and respond with timely, personalised support.
Maths anxiety is a significant challenge for students worldwide. While personalised assistance is widely regarded as the most effective way to address it, many teachers struggle to provide this level of support at scale in busy classrooms.
Lead researcher Dr Florence Gabriel said AI has the potential to transform how maths anxiety is addressed by offering tailored interventions that support both learning and student wellbeing.
“Maths anxiety is an emotional response characterised by fear, tension, and apprehension when a student is faced with a mathematical problem or test,” she said. “In some cases, it can be so paralysing that it limits a student’s learning and performance.”
“While it’s normal to feel some level of anxiety when encountering challenging subjects, excessive maths anxiety can lead to avoidance, reduced self-confidence and a loss of control – even long-term aversion to mathematical learning.”
The study suggests that when AI systems are designed with the right data and goals, they can adapt their responses to counter negative emotional experiences before they escalate.
According to the research, more than a third of adults and children experience maths anxiety. Those with the highest levels can perform almost four years behind peers with lower anxiety.
Dr Gabriel said tailored AI models could help students feel more capable and motivated.
“By helping students set realistic, motivating goals aligned with their individual capabilities, and by responding with encouragement when signs of frustration appear, AI can help students feel more competent, motivated and in control of their learning,” she said.
The research proposes a new model of mathematics learning in which emotional development is central to the design of AI systems. It suggests AI could support learning by:
- Tailoring activities by adjusting difficulty in real time
- Providing emotionally intelligent feedback when frustration or disengagement is detected
- Supporting student autonomy through goal-setting and personalised pathways
- Helping teachers with real-time insights for targeted interventions
Co-researcher Dr John Kennedy said AI models used in education must move beyond simply providing answers.
“Current AI models are trained to provide users with answers they’re happy with, but this can bypass the cognitive processes of learning,” he said.
“When students rely on tools that simply generate answers, they only learn how to prompt the system rather than how to think through a problem.
“We need to go beyond this basic use of AI and towards tools designed from the ground up for education – tools that understand local contexts, diverse learning goals and the emotional dimensions of learning.”
Dr Kennedy said effective educational AI should break problems into simpler steps and tailor both the hints and the emotional tone of responses.
“When AI can adapt to a learner’s emotional state as well as their cognitive needs, it brings us closer to truly supportive and intuitive learning tools,” he said.
The research team has made available an AI Maths tutor that that provides a working example of what AI can currently do in the classroom using simple prompts: https://app.chatmate.c3l.ai/temp-access/E2QqhaOZZC/
