Examining Student and AI Generated Personalized Analogies in Introductory Physics

TL;DR

This study investigates how introductory physics students and AI-generated content use personalized analogies to explain the Morse potential curve and how this varies when communicating to a non-expert audience versus the students' own contexts. By qualitatively analyzing around 800 student responses and AI outputs, it contrasts spontaneous student analogies with AI-generated ones, and examines self-generated analogies when students describe the curve in everyday contexts. The results show that spontaneous student analogies are relatively scarce, whereas AI produces analogies readily; students display notable creativity when explicitly asked to map to personal domains. The findings inform the potential of AI as a learning partner to support analogical reasoning in physics and highlight analogy-based sensemaking as a means to surface and address gaps in understanding.

Abstract

Comparing abstract concepts (such as electric circuits) with familiar ideas (plumbing systems) through analogies is central to practice and communication of physics. Contemporary research highlights self-generated analogies to better facilitate students' learning than the taught ones. "Spontaneous" and "self-generated" analogies represent the two ways through which students construct personalized analogies. However, facilitating them, particularly in large enrollment courses remains a challenge, and recent developments in generative artificial intelligence (AI) promise potential to address this issue. In this qualitative study, we analyze around 800 student responses in exploring the extent to which students spontaneously leverage analogies while explaining Morse potential curve in a language suitable for second graders and self-generate analogies in their preferred everyday contexts. We also compare the student-generated spontaneous analogies with AI-generated ones prompted by students. Lastly, we explore the themes associated with students' perceived ease and difficulty in generating analogies across both cases. Results highlight that unlike AI responses, student-generated spontaneous explanations seldom employ analogies. However, when explicitly asked to explain the behavior of the curve in terms of their everyday contexts, students employ diverse analogical contexts. A combination of disciplinary knowledge, agency to generate customized explanations, and personal attributes tend to influence students' perceived ease in generating explanations across the two cases. Implications of these results on the potential of AI to facilitate students' personalized analogical reasoning, and the role of analogies in making students notice gaps in their understanding are discussed.

Figures (10)

• Figure 1: The study's design framework adopted from United Nations Educational, Scientific and Cultural Organization's (UNESCO) guide. The framework has been slightly modified and the original flowchart can be found in sabzalieva2023chatgpt.
• Figure 2: The diagram of Morse potential curve provided to students during data collection.
• Figure 3: Details of our data. The elements within the solid line indicate the data from students whereas those within dotted lines correspond to the data which students generated from Generative-AI. The double headed arrow signifies students' comparison between each corresponding elements. The data also includes students' perceptions of the usefulness of the activity which has not been highlighted in the above figure.
• Figure 4: Pie charts highlighting the extent of comparisons observed in (a) students' explanations to second graders, (b) AI-generated explanations to second graders, (c) students' explanations in their preferred contexts.
• Figure 5: Word cloud representing the various analogical contexts employed by students when describing the Morse potential curve in a language suitable for second graders.