Marcos Abreu | Searcharxiv

arXiv2026

Exploring the potential of ChatGPT for feedback and evaluation in experimental physics

This study explores how generative artificial intelligence, specifically ChatGPT, can assist in the evaluation of laboratory reports in Experimental Physics. Two interaction modalities were implemented: an automated API-based evaluation and a customized ChatGPT configuration designed to emulate instructor feedback. The analysis focused on two complementary dimensions-formal and structural integrity, and technical accuracy and conceptual depth. Findings indicate that ChatGPT provides consistent feedback on organization, clarity, and adherence to scientific conventions, while its evaluation of technical reasoning and interpretation of experimental data remains less reliable. Each modality exhibited distinctive limitations, particularly in processing graphical and mathematical information. The study contributes to understanding how the use of AI in evaluating laboratory reports can inform feedback practices in experimental physics, highlighting the importance of teacher supervision to ensure the validity of physical reasoning and the accurate interpretation of experimental results.

physics.ed-ph↗

arXiv2025

Enhancing Kinematics Understanding Through a Real-Time Graph-Based Motion Video Game

Kinematics is a core topic in early physics courses, yet students often struggle to interpret motion and its graphical representations. To tackle these difficulties, we developed MissionMotion, a physical-computational videogame where students reproduce target motion graphs using real-time data from their own movements or from sensors connected through micro:bit or Arduino. The system displays both the target and the user-generated graph, providing immediate visual feedback and a score based on similarity. We piloted the environment with ninth-grade students in different school contexts and evaluated their experience using the MEEGA+ instrument. The results show strong engagement, positive perceptions of usability, and evidence that the game promotes reflection on motion graphs in ways that rarely emerge in traditional lessons. MissionMotion runs on any web-enabled device and all materials are openly available, offering teachers an accessible tool to integrate experimentation, computational thinking, and playful learning into physics classrooms.

physics.ed-ph↗

arXiv2025

Exploring the potential of ChatGPT for feedback and evaluation in experimental physics

This study explores how generative artificial intelligence, specifically ChatGPT, can assist in the evaluation of laboratory reports in Experimental Physics. Two interaction modalities were implemented: an automated API-based evaluation and a customized ChatGPT configuration designed to emulate instructor feedback. The analysis focused on two complementary dimensions-formal and structural integrity, and technical accuracy and conceptual depth. Findings indicate that ChatGPT provides consistent feedback on organization, clarity, and adherence to scientific conventions, while its evaluation of technical reasoning and interpretation of experimental data remains less reliable. Each modality exhibited distinctive limitations, particularly in processing graphical and mathematical information. The study contributes to understanding how the use of AI in evaluating laboratory reports can inform feedback practices in experimental physics, highlighting the importance of teacher supervision to ensure the validity of physical reasoning and the accurate interpretation of experimental results.

physics.ed-ph↗

arXiv2025

Enhancing Kinematics Understanding through a Video Game Based on Real-Time Motion Graphs

Interpreting kinematic graphs remains a significant challenge in physics education. The MissionMotion Project addresses this issue by providing a gamified physical-computational environment combining low-cost sensors, physical activity, computational thinking, and real-time visualization of motion graphs. This paper presents the design, development, and implementation of the project, with a particular focus on the pilot phase conducted with high school students in Uruguay. During this phase, we primarily used the MEEGA+ questionnaire to evaluate the gaming experience, usability, and motivation of the participants. Our analysis of the results shows high levels of satisfaction, perceived learning, and engagement, supporting the proposal's viability. Finally, we plan to conduct a large-scale conceptual evaluation to analyze how the proposal impacts understanding of kinematic graphs using standardized assessment tools.

physics.ed-ph↗

arXiv2024

Light intensity does not always decay with the inverse of the square of the distance: an open-inquiry laboratory

The square inverse law with distance plays an important role in many fields of physics covering electromagnetism, optics or acoustics. However, as every law in physics has its range of validity. We propose an open-inquiry laboratory where we challenge these concepts by proposing experiments where the intensity of light decays linearly or even remains constant over a range of distances. Using the light sensors built into smartphones, it is possible to measure light curves for different sources: point, linear, planar and even LED ring lights. The analysis of these curves allows us to discuss the limits of the physical theories. This low-cost laboratory, initially proposed in the context of the COVID19 pandemic, has the virtue of challenging intuition and encouraging the critical spirit of the students.

physics.ed-ph↗