Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM63541
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Master Of Computer Application
Bapuji Institute of Engineering and Technology
Master Of Computer Application
Bapuji Institute of Engineering and Technology
This project is (NLP) and modern language modelling techniques, which form key components of artificial intelligence (AI). The contemporary digital landscape faces a dual challenge: the critical need for large-scale, cross-institutional data synthesis and the stringent regulatory requirements of data privacy (GDPR/HIPAA). This project proposes a Federated Big Data Platform engineered to resolve the "Privacy-Utility Paradox" by shifting from a centralized data-lake model to a decentralized, privacypreserving architecture. By deploying lightweight "Spoke" clients at local healthcare and educational institutions, the platform enables In-Situ Machine Learning, where only non-identifiable model parameters traverse the network. This "Privacy-by-Design" approach drastically reduces the risk of data exfiltration while fostering institutional trust and global collaboration. Parallel to this infrastructural shift, the platform integrates an Automated Educational Assessment System designed to democratize and scale academic evaluation. (NLP) architectures—including BERT for semantic parsing and GPT for generative synthesis—the system transforms static learning materials into comprehensive, Bloom-aligned assessments. By mapping content to cognitive levels ranging from basic recall to higher-order evaluative reasoning, the system reduces the administrative burden on educators and provides learners with personalized, adaptive practice tools. Initial evaluations demonstrate that the federated model achieves over 95% accuracy compared to centralized benchmarks, while the automated assessment engine significantly enhances question diversity and pedagogical alignment. Ultimately, this dual-purpose framework serves as a scalable blueprint for a more equitable, secure, and intelligent global health and education ecosystem.
KEYWORDS
The project “Question Generation for Educational Content” was developed to build an intelligent system capable of automatically creating quality educational questions using Artificial Intelligence (AI) and Natural Language Processing (NLP6.1 Project Summary and Success Metrics ) The development of the AI-Driven Question Generation System successfully addresses the chronic efficiency gap in academic assessment design. By transitioning from manual question curation to an automated, NLP-powered pipeline, the project demonstrates that high-fidelity evaluation materials can be generated with a fraction of the traditional temporal investment. In conclusion, this project represents a significant milestone in the integration of Educational Technology (EdTech) and Artificial Intelligence. By automating the more redundant aspects of the teaching cycle, the system does not replace the educator; rather, it acts as a sophisticated cognitive assistant that liberates the instructor to focus on mentorship and curriculum innovation. The successful execution of this tool has proved that it is feasible to use deep-learning techniques for creating an adaptive, highly scalable, and quality educational environment. Moving ahead, as universities are growing towards an online educational framework, this system is ready to cater to the requirements of modern teaching.
1. RoBERTa: A Robustly Optimised BERT Pretraining Approach. arXiv:1907.11692. 2. Rajpurkar, P., Zhang, J., Lopyrev, K., & Liang, P. (2016). EMNLP. 3. OpenAI (2024). OpenAI Research. 4. Agarwal, M., & Batra, S. (2022). and Deep Learning. Applications. 5. Mishra, A., & Jain, S. (2021). Educational Content Generation using Artificial Intelligence. IEEE Access Journal. 6. Kumar, R., & Sharma, P. (2020). AI-Powered Assessment Tools for the Education Sector. International Journal of Computer Applications. 7. Google AI Research (2022). T5: Exploring the Limits of Transfer Learning with a Unified Text to Text Transformer. 8. Cambridge University Press (2021). Applications of NLP E-Learning. 9. Hugging Face (2023). Transformers: Natural Language Processing Library. 10. GitHub Repository (2024). Automatic Question Generation using NLP.
Publication Date
5/21/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
2
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...