Harnessing AI for Educational Excellence: A Comparative Analysis of DeepSeek and ChatGPT in Social Science Teaching and Learning
DOI:
https://doi.org/10.62997/psi.2025a-41065Keywords:
DeepSeek, ChatGPT, AI in Education, Social Science Teaching, Learning Outcomes, Comparative Analysis, .Phil./PhD Research, Qurtuba University, Academic Performance, AI-assisted LearningAbstract
The research assesses the relative effectiveness of DeepSeek and ChatGPT tools for social science postgraduate education with MPhil and PhD scholars from Qurtuba University situated in Dera Ismail Khan. The research project uses both quantitative analysis of learning results and qualitative student surveys to study the two AI tools. The study shows DeepSeek generates better academic results when compared to ChatGPT because students scored 25.9% higher in their post-test while scoring 17.7% with ChatGPT, and both results were statistically significant (p = 0.005). The evaluation from students demonstrated that DeepSeek outperformed ChatGPT regarding the tools' accuracy in information delivery as well as their capacity to provide detailed explanations and facilitate meaningful student learning. Nevertheless, students favoured ChatGPT because of its interactive communication capabilities and fast response time. The tools contain a combination of challenges since they sometimes provide out-of-date references and both lack adequate academic citations. Research indicates that DeepSeek stands above ChatGPT for conducting academic investigations, yet students find ChatGPT superior for interactive educational sessions. The proposed directions focus on integrating DeepSeek for thesis assistance as well as deploying ChatGPT for discussions, although better citation capabilities need improvement in the current AI tools. The findings deliver essential direction to teachers, AI developers, and education authorities who want to improve the effectiveness of AI-based learning methods in higher education institutions.
References
Alto, V. (2023). Modern Generative AI with ChatGPT and OpenAI Models: Leverage the capabilities of OpenAI's LLM for productivity and innovation with GPT3 and GPT4. Packt Publishing Ltd.
Barton, K. C., & Avery, P. G. (2016). Research on social studies education: Diverse students, settings, and methods. Handbook of Research on Teaching, 985-1038. https://doi.org/10.3102/978-0-935302-48-6_16
Baydemir, R. (2025). Artificial Intelligence Wars in Global Technology: ChatGPT vs. DeepSeek.
Božić, V. (2024). Artificial Intelligence in Nurse Education. In Engineering Applications of Artificial Intelligence (pp. 143-172). Cham: Springer Nature Switzerland.
Cui, J. (2025). The impact of general artificial intelligence on University students' research and technological innovation: A case study of DeepSeek AI and ChatGPT. The Educational Review, USA, 1-15. https://doi.org/10.2139/ssrn.5179907
Dare, E. A., Keratithamkul, K., Hiwatig, B. M., & Li, F. (2021). Beyond content: The role of STEM disciplines, real-world problems, 21st century skills, and STEM careers within science teachers’ conceptions of integrated STEM education. Education Sciences, 11(11), 737. https://doi.org/10.3390/educsci11110737
Fitria, T. N. (2023). The use of artificial intelligence in education (Aied): Can AI replace the teacher's role? EPIGRAM (e-journal), 20(2), 165-187. https://doi.org/10.32722/epi.v20i2.5711
Khosravi, H., Shum, S. B., Chen, G., Conati, C., Tsai, Y., Kay, J., Knight, S., Martinez-Maldonado, R., Sadiq, S., & Gašević, D. (2022). Explainable artificial intelligence in education. Computers and Education: Artificial Intelligence, 3, 100074. https://doi.org/10.1016/j.caeai.2022.100074
Kotsis, K. T. (2025). ChatGPT and DeepSeek evaluate one another for science education. EIKI Journal of Effective Teaching Methods, 3(1). https://doi.org/10.59652/jetm.v3i1.439
Novitsky, M. (2024). Can AI help make us better people? Exploring AI for enhanced moral education in early education (Master's thesis, University of Twente).
Pan, C., Banerjee, J. S., De, D., Sarigiannidis, P., Chakraborty, A., & Bhattacharyya, S. (2023, February). ChatGPT: An Openai platform for society 5.0. In Doctoral Symposium on Human Centred Computing (pp. 384-397). Singapore: Springer Nature Singapore.
Pedro, F., Subosa, M., Rivas, A., & Valverde, P. (2019). Artificial intelligence in education: Challenges and opportunities for sustainable development. https://unesdoc.unesco.org/ark:/48223/pf0000366994
Singh, A. (2024). The future of learning: AI-driven personalized education. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.5076438
Syahrizal, S., Yasmi, F., & Mary, T. (2024). AI-enhanced teaching materials for education: A shift towards digitalization. International Journal of Religion, 5(1), 203-217. https://doi.org/10.61707/j6sa1w36
Yu, H. (2025). The application and challenges of ChatGPT in educational transformation: New demands for teachers' roles. Heliyon, 11(9), e43319. https://doi.org/10.1016/j.heliyon.2025.e43319
Zhai, X. (2025). DeepSeek: Transforming the foundations of education. https://doi.org/10.20944/preprints202503.1776.v1
