Chatbot Iris Offers Individual Support

A packed auditorium with over 1000 students. This is not a rare sight in introductory informatics lectures. To meet the needs of each individual student under these conditions, Stephan Krusche, professor of Software Engineering, and his team have been building the Artemis learning platform since 2016. It resembles well-known learning platforms, but offers more possibilities. For example, students not only receive their assignments through the platform, but also get immediate feedback when they make mistakes or show an incomplete understanding of concepts.

In October of last year, Stephan Krusche’s team at the TUM Centre for Educational Technologies added the chatbot to the platform. Iris is based on the GPT large language model of OpenAI. It is intended to help students with assigned problems, with the support geared to their individual needs. To adapt the system to the learning context, the chatbot operates as a so-called excellent tutor. That means that, rather than immediately suggesting the right solution or specific steps, Iris offers subtle hints or asks leading questions. This approach encourages students to think for themselves. To boost learning efficiency, the chatbot only answers questions directly relevant to the learning content.

"To test the success of Iris, we surveyed over 200 students from three introductory informatics lectures," says Patrick Bassner, a doctoral candidate at the Chair of Software Engineering. "The goal was to arrive at conclusions on how students rate the effectiveness of the support from Iris, whether students are more comfortable asking a chatbot questions than a human tutor and whether students subjectively trust Iris."

The responses show that the students value Iris as a valuable support, but also that a large share of those surveyed still rely on human tutors. The chatbot understands questions well and students feel comfortable and safe when using it. Iris gives them the feeling that the chats will remain private and that they are not being judged when asking questions. Especially in large lectures, this saves students from having to overcome their inhibitions to ask questions in front of the class. When studying for exams, the use of Iris is becoming commonplace. However, students feel confident enough to solve problems on exams without the support of the chatbot.

"The integration of Iris into Artemis has shown that AI-controlled tutors can play a valuable role in university teaching," says Stephan Krusche. "They offer personalized support that benefits learning and boosts students' ability to help themselves."

The researchers plan to further optimize the chatbot Iris and want to see it being used in other subject areas.

Patrick Bassner, Eduard Frankford, Stephan Krusche.
Iris: An AI-Driven Virtual Tutor for Computer Science Education.
In Proceedings of the 2024 on Innovation and Technology in Computer Science Education V. 1 (ITiCSE 2024). Association for Computing Machinery, 2024. doi: 10.1145/3649217.3653543

Most Popular Now

AI-Powered CRISPR could Lead to Faster G…

Stanford Medicine researchers have developed an artificial intelligence (AI) tool to help scientists better plan gene-editing experiments. The technology, CRISPR-GPT, acts as a gene-editing “copilot” supported by AI to help...

Groundbreaking AI Aims to Speed Lifesavi…

To solve a problem, we have to see it clearly. Whether it’s an infection by a novel virus or memory-stealing plaques forming in the brains of Alzheimer’s patients, visualizing disease processes...

AI Spots Hidden Signs of Depression in S…

Depression is one of the most common mental health challenges, but its early signs are often overlooked. It is often linked to reduced facial expressivity. However, whether mild depression or...

AI Tools Help Predict Severe Asthma Risk…

Mayo Clinic researchers have developed artificial intelligence (AI) tools that help identify which children with asthma face the highest risk of serious asthma exacerbation and acute respiratory infections. The study...

AI Model Forecasts Disease Risk Decades …

Imagine a future where your medical history could help predict what health conditions you might face in the next two decades. Researchers have developed a generative AI model that uses...

AI Model Indicates Four out of Ten Breas…

A project at Lund University in Sweden has trained an AI model to identify breast cancer patients who could be spared from axillary surgery. The model analyses previously unutilised information...

ChatGPT 4o Therapeutic Chatbot 'Ama…

One of the first randomized controlled trials assessing the effectiveness of a large language model (LLM) chatbot 'Amanda' for relationship support shows that a single session of chatbot therapy...

AI Distinguishes Glioblastoma from Look-…

A Harvard Medical School–led research team has developed an AI tool that can reliably tell apart two look-alike cancers found in the brain but with different origins, behaviors, and treatments. The...

Smart Device Uses AI and Bioelectronics …

As a wound heals, it goes through several stages: clotting to stop bleeding, immune system response, scabbing, and scarring. A wearable device called "a-Heal," designed by engineers at the University...

Overcoming the AI Applicability Crisis a…

Opinion Article by Harry Lykostratis, Chief Executive, Open Medical. The government’s 10 Year Health Plan makes a lot of the potential of AI-software to support clinical decision making, improve productivity, and...

Dartford and Gravesham Implements Clinis…

Dartford and Gravesham NHS Trust has taken a significant step towards a more digital future by rolling out electronic test ordering using Clinisys ICE. The trust deployed the order communications...