International Journal of Social Science & Economic Research
Submit Paper

Title:
Comparing the Relative Effectiveness of Chat GPT-generated Content and Human-generated Videos for Teaching Students Calculus

Authors:
Srijan Challapalli and John Leddo

|| ||

Srijan Challapalli and John Leddo
MyEdMaster, LLC Virginia, USA

MLA 8
Challapalli, Srijan, and John Leddo. "Comparing the Relative Effectiveness of Chat GPT-generated Content and Human-generated Videos for Teaching Students Calculus." Int. j. of Social Science and Economic Research, vol. 9, no. 11, Nov. 2024, pp. 5434-5446, doi.org/10.46609/IJSSER.2024.v09i11.031. Accessed Nov. 2024.
APA 6
Challapalli, S., & Leddo, J. (2024, November). Comparing the Relative Effectiveness of Chat GPT-generated Content and Human-generated Videos for Teaching Students Calculus. Int. j. of Social Science and Economic Research, 9(11), 5434-5446. Retrieved from https://doi.org/10.46609/IJSSER.2024.v09i11.031
Chicago
Challapalli, Srijan, and John Leddo. "Comparing the Relative Effectiveness of Chat GPT-generated Content and Human-generated Videos for Teaching Students Calculus." Int. j. of Social Science and Economic Research 9, no. 11 (November 2024), 5434-5446. Accessed November, 2024. https://doi.org/10.46609/IJSSER.2024.v09i11.031.

References

[1] . Ahmad, M. & Leddo, J. (2023). The effectiveness of Cognitive Structure Analysis in assessing students’ knowledge of the scientific method. International Journal of Social Science and Economic Research, 8(8), 2397-2410.
[2] . Bahl, K., Bahl, K & Leddo, J. (2018). Optimizing homework for high aptitude students. International Journal of Advanced Educational Research, 3(5), 27-30.
[3] . Bhandarkar, S., Leddo, J. & Banerjee, M. (2016). Comparing the relative effects of homework on high aptitude vs. average aptitude students. International Journal of Humanities and Social Science Research, 2(9), 59-62.
[4] . Cynkin, C. and Leddo, J. (2023). Teaching students to self-assess using Cognitive Structure Analysis: Helping students determine what they do and do not know. International Journal of Social Science & Economic Research, 08(09), 3009-3020.
[5] . Dandemraju, A., Dandemraju, R., & Leddo, J. (2024). Teaching students to self-assess their knowledge of chemistry using cognitive structure analysis. International Journal of Social Science & Economic Research, 09(02), 541–549.
[6] . Halaweh, M. (2023). ChatGPT in education: Strategies for responsible implementation. Contemporary Educational Technology, 15(2), ep421.
[7] . Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial Intelligence in Education: Promises and Implications for Teaching and Learning. Center for Curriculum Redesign.
[8] . Leddo, J. & Ahmad, M. (2024). Do you want to raise student achievement? Then, assess and remediate student knowledge, not student performance. International Journal of Social Science and Economic Research, 9(1), 249-261.
[9] . Leddo, J., Hong, Q., Shyamala, N. & Xue, A. (2019). Improving SAT reading scores by using metacognitive reading strategies. International Journal of Advanced Educational Research, 4(4), 91-93.
[10] . Leddo, J., Li, S.and Zhang, Y. (2022) Cognitive Structure Analysis: A Technique For Assessing What Students Know, Not Just How They Perform. International Journal of Social Science and Economic Research, 7(11), 3716-3726.
[11] . Leddo, J., Sangela, S. & Bekkary, A. (2021). Improving SAT math scores by using metacognitive problem-solving strategies. International Journal of Social Science and Economic Research, 6(3), 1044-1053.
[12] . Leddo, J., Sengar, A., Liang, I. & Chilumula, R. (2020). Improving SAT writing and language scores by using metacognitive strategies. International Journal of Advanced Educational Research, 5(1), 24-26.
[13] . Luckin, R., Holmes, W., Griffiths, M., & Forcier, L. B. (2016). Intelligence Unleashed: An Argument for AI in Education. Pearson.
[14] . Mahajan, L., Chadeva, A. & Leddo, J. (2021). Evaluating procedural and conceptual teaching formats for beginning and advanced programming students. International Journal of Social Science and Economic Research, 6(4), 1356-1365.
[15] . Moore, S., Nguyen, H. A., Bier, N., Domadia, T., Stamper, J. (2022). Assessing the quality of student-generated short answer questions using GPT-3. In Educating for a New Future: Maing Sense of Technology-Enhanced Learning Adoption: 17th European Conference on Technology Enhanced Learning, EC-TEL 2022.
[16] . Namilae, A & Leddo, J. (2024). Comparing the Effectiveness of Chat GPT and Teacher-generated Content for Teaching Students. International Journal of Social Science and Economic Research, 9(7), 2554-2564.
[17] . National Assessment of Educational Progress. Retrieved from www.nationsreportcard.gov. Ni, L., et al. (2022). Deepqr: Neural-based quality ratings for learner sourced multiple-choice questions. Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12826–12834.
[18] . PebbleGO. pgoplayer.pebblego.com/. Accessed 1 July 2024.
[19] . Sarsa, S., Denny, P., Hellas, A., Leinonen, J. (2022). Automatic generation of programming exercises and code explanations using large language models. In Proceedings of the 2022 ACM
[20] . Ravi, D & Leddo, J. (2024). Improving Student Performance by Having Students Assess and Remediate Their Own Knowledge Deficiencies. International Journal of Social Science and Economic Research, 9(10), 4717-4724.
[21] . Singh, A., Brooks, C., Doroudi, S. (2021). Learnersourcing in theory and practice: Synthesizing the literature and charting the future. In Proceedings of the Eighth ACM Conference on Learning@ Scale.
[22] . Wang, E., Ailneni, A. & Leddo, J. (2021).Improving mathematics learning by adding conceptual to procedural instruction. International Journal of Social Science and Economic Research, 6(9), 3491-3498.
[23] . Wang, Z., Valdez, J., Basu Mallick, D., Baraniuk, R. G. (2022). Towards human-like educational question generation with large language models. In Artificial Intelligence in Education: 23rd International Conference, AIED 2022.

ABSTRACT:
The presented research investigates and compares the relative effectiveness of Artificial Intelligence, specifically large language models (ChatGPT) and human-generated videos in teaching students the calculus topic of derivatives. 30 randomly chosen high school students were taught derivatives. 15 of them were taught through Chat GPT and the other 15 were taught through traditional educational videos. All participants of the study were given a post-test after they learned their topics. The results showed that students who learned from ChatGPT scored higher on their post-tests than did students who used human-generated videos. These results imply that using Chat GPT to learn is more effective, efficient, and overall more personalized to each individual student. Implementing AI into classrooms could enhance the learning process for students all over the world.

IJSSER is Member of