Authors : N. Divya; Jennifer Mary S.; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/2ubcv7h8

Scribd : https://tinyurl.com/mry778hr

DOI : https://doi.org/10.38124/ijisrt/26apr1845

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : This paper presents EduAssist, a lightweight, multilingual college enquiry assistant implemented as a Flask web application and designed for easy deployment and maintainability. EduAssist couples a deterministic, rule-based natural language understanding module with a small set of manually authored multilingual reply templates to ensure consistent, factual answers for high-value intents (fees, admissions, hostel, placements). The system uses LibreTranslate for language detection and translation, gTTS for on-demand text-to-speech synthesis, and SQLAlchemy/MySQL for persistent storage of users, courses, placements, events, FAQs and query logs. A responsive browser client provides a chat UI with optional Web Speech API voice input and automatic audio playback of server-generated responses. The architecture emphasizes portability (minimal external dependencies), auditability (stored query logs for analytics and iterative improvement), and accessibility (text + voice replies in English, Hindi, Kannada, Tamil and Telugu). We describe the data model, intent matching heuristics, translation/TTS flows, and practical deployment considerations. A functional evaluation using seeded demo data demonstrates reliable handling of typical campus enquiries with low operational complexity, and highlights directions for future work such as lightweight intent classification, asynchronous TTS generation, and on-premise translation to improve latency and privacy.

Keywords : Multilingual Chatbot, Flask Application, Rule-Based NLP, Text-to-Speech (TTS), Machine Translation, Campus Enquiry System, SQLAlchemy Database, Web Speech Interface, Lightweight Architecture, Educational Information Systems.

References :

1. J. Weizenbaum, “ELIZA—A computer program for the study of natural language communication between man and machine,” Communications of the ACM, vol. 9, no. 1, pp. 36–45, 1966.
2. R. Dale, “The return of the chatbots,” Natural Language Engineering, vol. 22, no. 5, pp. 811–817, 2016.
3. M. Nuruzzaman and O. K. Hussain, “A survey on chatbot implementation in customer service industry through deep neural networks,” Proceedings of IEEE 17th International Conference on Industrial Informatics, pp. 799–804, 2019.
4. A. P. Rodrigues and S. P. Kumar, “Rule-based conversational agents for academic enquiry automation,” International Journal of Computer Applications, vol. 176, no. 29, pp. 1–6, 2020.
5. S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. O’Reilly Media, 2009.
6. F. Casati et al., “Web service architectures and their application in education portals,” IEEE Internet Computing, vol. 6, no. 5, pp. 24–31, 2002.
7. A. Vaswani et al., “Attention is all you need,” Advances in Neural Information Processing Systems, pp. 5998–6008, 2017. (Used in related work context; not implemented in this project.)
8. LibreTranslate Documentation, “Open-source neural machine translation API,” 2024. [Online]. Available: https://libretranslate.com
9. Google Text-to-Speech (gTTS) Library, “Python interface for Google Translate TTS,” 2024. [Online]. Available: https://pypi.org/project/gTTS
10. Flask Documentation, “Lightweight WSGI web application framework,” 2024. [Online]. Available: https://flask.palletsprojects.com
11. SQLAlchemy Documentation, “Python SQL toolkit and Object Relational Mapper,” 2024. [Online]. Available: https://www.sqlalchemy.org
12. Web Speech API, “SpeechRecognition interface,” Mozilla Developer Network (MDN), 2024. [Online]. Available: https://developer.mozilla.org