Impacts of Anthropomorphizing Large Language Models in Learning Environments
Kristina Schaaff, Marc-André Heidelmann
TL;DR
The paper investigates how anthropomorphizing LLMs in learning environments affects educational theory, learner emotions, and learning outcomes. It grounds the analysis in the Media Equation and transformational education, identifying factors across the learning agent, learner, and environment that drive anthropomorphism. A two-system comparative design is proposed, with anthropomorphized and non-anthropomorphized LLMs tested via a decision-making task, a large student cohort, and emotion–performance assessments. The work discusses potential benefits such as enhanced engagement and personalized feedback, alongside risks like unrealistic expectations and emotional discomfort, and advocates for guidelines that balance relatability with realism to inform ethical, effective AI-supported education.
Abstract
Large Language Models (LLMs) are increasingly being used in learning environments to support teaching-be it as learning companions or as tutors. With our contribution, we aim to discuss the implications of the anthropomorphization of LLMs in learning environments on educational theory to build a foundation for more effective learning outcomes and understand their emotional impact on learners. According to the media equation, people tend to respond to media in the same way as they would respond to another person. A study conducted by the Georgia Institute of Technology showed that chatbots can be successfully implemented in learning environments. In this study, learners in selected online courses were unable to distinguish the chatbot from a "real" teacher. As LLM-based chatbots such as OpenAI's GPT series are increasingly used in educational tools, it is important to understand how the attribution processes to LLM-based chatbots in terms of anthropomorphization affect learners' emotions.