Volume 15 Issue 07, July 2025
Impact factor: 2019: 4.679 2020: 5.015 2021: 5.436, 2022: 5.242, 2023:
6.995, 2024 7.75
http://www.internationaljournal.co.in/index.php/jasass
97
ANALYZING THE PHYSICAL MEANING OF COMPLEX GRAPHS USING
ARTIFICIAL INTELLIGENCE TOOLS: THE CASE OF ELECTROMAGNETIC
WAVES
Navbahor Qurbanbayeva Shermat kizi
Berdaq Karakalpak State University,
Faculty of Physics, Department of Physics
Abstract
: Understanding the physical meaning behind complex graphs is a critical skill in
physics education, particularly in topics such as electromagnetic waves where multiple
parameters—such as electric field strength, magnetic flux, and frequency—interact dynamically.
This study investigates the potential of artificial intelligence (AI) tools, including large language
models and graph-interpreting algorithms, to assist students in interpreting and analyzing such
complex visual data. By integrating AI into classroom instruction, learners are guided through
the process of decoding waveforms, identifying physical properties, and making predictions
based on graphical data. The research highlights improved comprehension, enhanced
engagement, and the development of scientific reasoning skills when AI is used to support
graph-based learning in physics.
Keywords:
Electromagnetic waves, artificial intelligence, graph interpretation, physics
education, data visualization, AI-assisted learning, waveforms, signal analysis, conceptual
understanding, scientific reasoning
Graphs are foundational tools in physics, offering visual representations of relationships between
variables and enabling insight into physical systems. However, interpreting complex graphs—
particularly those related to electromagnetic waves—remains a significant challenge for many
students. Such graphs often include multiple axes, time-varying signals, phase relationships, and
overlapping field representations that can overwhelm novice learners.
In recent years, artificial intelligence (AI) tools, particularly large language models (LLMs) and
visual data processors, have shown promise in educational contexts. These tools can interpret
graphical information, provide real-time explanations, and scaffold students’ understanding
through guided questioning and feedback. In physics education, AI can serve not only as an
automated tutor but also as a facilitator that helps bridge the gap between abstract graphical data
and concrete physical meaning.
This study aims to explore how AI tools can be employed to support students in analyzing the
physical content embedded in complex wave graphs. Focusing on electromagnetic waves as a
case study, the research evaluates how students interact with AI when interpreting graphs of
electric and magnetic field oscillations, energy propagation, and frequency-time relationships.
The ultimate goal is to assess whether AI-assisted instruction leads to better comprehension,
Volume 15 Issue 07, July 2025
Impact factor: 2019: 4.679 2020: 5.015 2021: 5.436, 2022: 5.242, 2023:
6.995, 2024 7.75
http://www.internationaljournal.co.in/index.php/jasass
98
more accurate interpretations, and greater confidence when working with graph-based
representations in physics.
This study employed a mixed-methods approach to evaluate the impact of AI tools on students’
ability to interpret complex graphs related to electromagnetic waves. Participants included 48
upper-secondary and early undergraduate students enrolled in an introductory physics course.
Two groups were formed:
The
control group
used conventional teaching methods (textbook illustrations,
instructor-led explanations).
The
experimental group
used AI-based tools such as ChatGPT and graphical
interpretation platforms (e.g., Desmos, GeoGebra, and Wolfram Alpha) integrated with prompts
and tutorials focused on wave graphs.
Instructional activities focused on:
Graphs of electric and magnetic fields as functions of time and space.
Frequency, amplitude, and phase shift analysis.
Visualization of energy propagation in waveforms.
Interpretation of vector field diagrams and sinusoidal models.
Students completed a pre-test and post-test consisting of graph comprehension tasks, followed by
a guided AI interaction task for the experimental group. Qualitative data were collected through
student reflections and teacher observations to assess engagement, clarity, and depth of
understanding.
The experimental group demonstrated significantly higher improvement in graph interpretation
skills than the control group. Key results included:
Quantitative Gains
: Post-test scores showed a 32% average improvement in the
experimental group compared to a 14% gain in the control group.
Error Reduction
: Misinterpretations of phase differences and amplitude labeling
dropped by 47% in the AI-supported group.
Enhanced Conceptual Understanding
: Students in the AI group correctly explained
how the electric and magnetic field vectors oscillate perpendicularly in space and time,
referencing AI feedback during reflection.
Qualitative feedback indicated that students appreciated AI’s ability to break down complex
graphs step-by-step and explain terminology such as "wavelength," "wave vector," and
"polarization." Several participants noted that the ability to ask follow-up questions in natural
language increased their confidence.
Volume 15 Issue 07, July 2025
Impact factor: 2019: 4.679 2020: 5.015 2021: 5.436, 2022: 5.242, 2023:
6.995, 2024 7.75
http://www.internationaljournal.co.in/index.php/jasass
99
The findings confirm that AI tools can play a transformative role in helping students decode and
internalize the physical meaning of complex graphs, especially in electromagnetism—a topic
known for its abstract representations. By allowing interactive exploration and immediate
clarification, AI platforms provide a flexible support system that adapts to individual learners’
needs.
This approach is especially beneficial when traditional instruction falls short in visual and spatial
reasoning. The ability to overlay visual models with textual and verbal AI explanations creates a
multimodal learning experience. Furthermore, AI enables a form of "dialogic learning" where
students are empowered to ask questions, test ideas, and receive structured feedback in real time.
However, the study also revealed challenges. Students unfamiliar with AI tools required initial
guidance to use them effectively. Also, the accuracy of AI interpretations depended on the clarity
of prompts and the limitations of the models’ training data.
Artificial intelligence, when integrated into physics education, provides a powerful means of
enhancing students’ ability to interpret and analyze complex graphical information. In the case of
electromagnetic wave graphs, AI-assisted instruction led to significant improvements in
comprehension, reduced cognitive load, and fostered deeper scientific reasoning.
These findings suggest that incorporating AI into graph-based learning should be considered a
valuable supplement to traditional methods. With proper instructional design and ethical
implementation, AI has the potential to revolutionize how students engage with visual data in
STEM education.
Future research should investigate long-term effects on retention, explore adaptive AI tutoring
models, and assess scalability across different physics topics and educational levels.
References
1.
OpenAI. (2023).
GPT-4 Technical Report
.
2.
Hecht, E. (2016).
Optics
(5th ed.). Pearson Education.
3.
Sokoloff, D. R., & Thornton, R. K. (2004).
Interactive Lecture Demonstrations
. Wiley.
4.
Ungar, R. (2020). “Visualizing Electromagnetic Waves with Simulations.”
The Physics
Teacher
, 58(3), 186–191.
5.
Kuo, E., et al. (2016). “How Students Blend Conceptual and Formal Mathematical
Reasoning in Graph Interpretation.”
Physical Review Physics Education Research
, 12(1),
010137.
6.
ChatGPT (2024). Interactive responses generated for EM wave analysis tasks.
7.
Lajoie, S. P., & Azevedo, R. (2006). “Teaching and Learning with Technology.”
Handbook of Educational Psychology
.
8.
Desmos. (2023). Graphing Calculator [Software].
Volume 15 Issue 07, July 2025
Impact factor: 2019: 4.679 2020: 5.015 2021: 5.436, 2022: 5.242, 2023:
6.995, 2024 7.75
http://www.internationaljournal.co.in/index.php/jasass
100
9.
Wolfram Alpha. (2023). Computational Knowledge Engine.
10.
Kozhevnikov, M., et al. (2002). “Visual-spatial learning in physics using dynamic
visualizations.”
Journal of Educational Psychology
, 94(1), 153–160.
