Automatic feedback and hints on steps students take when learning how to program
Decanato - Facoltà di scienze informatiche
Data: 28 Settembre 2023 / 11:00 - 12:00
USI East Campus, Room D0.02
Speaker: Prof. Johan Jeuring, Utrecht University
Abstract: Every year, millions of students learn how to write programs. Learning activities for beginners almost always include programming tasks that require a student to write a program to solve a particular problem. When learning how to solve such a task, many students need feedback on their previous actions, and hints on how to proceed. For tasks such as programming, which are most often solved stepwise, the feedback should take the steps a student has taken towards implementing a solution into account, and the hints should help a student to complete or improve a possibly partial solution. There are many environments that support beginners learning how to program, including intelligent tutoring systems, online coding environments, tools based on large language models such as ChatGPT and Github Copilot, and educational games. Some of these learning environments give immediate automatic feedback on potentially partial student solutions, and hints on how to proceed with a partial solution. Feedback and hints need to be of good quality to support learning. But when do students need feedback and hints when learning how to program, how should it be given, and how can it be automatically calculated? Designers of learning environments make different choices here. How can we evaluate the quality of the feedback and hints provided by the different learning environments? In this talk I will give an overview of the approaches to automatic feedback and hints on programming steps, discuss our research on how to evaluate the quality of feedback and hints, and how to calculate them automatically. I will also take the opportunity to involve the audience in some of the dilemmas we are facing.
Biography: Johan Jeuring is a professor of Software Technology for Learning and Teaching, at the Department of Information and Computing Sciences and the Freudenthal Institute of Utrecht University. He also holds a minor appointment as CSO of DialogueTrainer, a company that sells software for practicing communication skills. He studies various aspects of computing education, develops software technology to support learning and teaching such as feedback in tutoring systems for programming, mathematics and logic, and develops the AI in several projects in the Dutch Lab for AI in Education. His work is used in several learning environments, both in the Netherlands and other European countries.
Host: Prof. Matthias Hauswirth