Serious Games & Pedagogical Agents for Teaching Machine Learning

Open Human-Computer Interaction Master Project Thesis No Affiliation

Background

Machine learning is becoming increasingly prevalent in our daily lives and has grown to be one of the most important topics in science. Many schools and universities already teach it as part of their curricula. Unfortunately, students perceive machine learning and their inner workings as hard to learn and understand. Teaching these concepts could be assisted with Serious Games, which are games used for purposes other than mere entertainment, e.g., learning (1). These games envelop the concepts they want to teach in-game mechanics and require the players to repeatedly apply them, supporting learning by repetition and generating flow (2). They have been shown to improve the high-level understanding of the enveloped concepts (3). Pedagogical Agents have also been shown to be beneficial in learning applications. They support learning by offering explanations and guidance, giving feedback, and motivating students. They positively affect learning performance and have been shown to increase student motivation (4). They are beneficial in more complex topics (5) and are thus also suitable for helping students learn machine learning.

This project or thesis is concerned with further developing Traversing the Pass, a serious game about the basics of machine learning enhanced with pedagogical agents (6). Possible further developments are restructuring the gameplay to resemble a factory builder or evaluating the effect of different pedagogical agents on learning outcomes.

Tasks

This project will focus on the following tasks:

• Literature research about the theoretical background
• Continue the development of the existing desktop prototype
• Execution of a user study to investigate possible learning effects
• Evaluation and presentation of results

Prerequisites

• Experience with the Unity game engine
• Experience with conducting user studies
• Basic knowledge of machine learning and backpropagation

Literature

• 1: Sara De Freitas and Fotis Liarokapis. 2011. Serious games: a new paradigm for education? In Serious games and edutainment applications. Springer, 9–23.
• 2: James Paul Gee. 2003. What video games have to teach us about learning and literacy. Computers in Entertainment (CIE) 1, 1 (2003), 20–20
• 3: Chelsea M. Myers, Jiachi Xie, and Jichen Zhu. 2020. A Game-Based Approach for Helping Designers Learn Machine Learning Concepts. (2020).
• 4: Gonca Kizilkaya and Petek Askar. 2008. The Effect of an Embedded Pedagogical Agent on the Students’ Science Achievement. Interactive Technology and Smart Education 5, 4 (Jan. 2008), 208–216.
• 5: W. Lewis Johnson, Jeff W. Rickel, and James C. Lester. 2000. Animated Pedagogical Agents: Face-to-Face Interaction in Interactive Learning Environments. International Journal of Artificial Intelligence in Education 11 (2000), 47–78
• 6: Philipp Krop, Sebastian Oberdörfer, Marc Erich Latoschik. 2023. Traversing the Pass: Improving the Knowledge Retention of Serious Games Using a Pedagogical Agent. In Proceedings of the 23rd International Conference on Intelligent Virtual Agents (IVA) (2023).

Contact Persons at the University Würzburg