Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68596
Volume:
10 |
10 |
Oct 2026
Pages:
1-4
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.
Department of Master of Computer Application,
JCEI’s Jaihind Institute of Management and Research, Vadgaon Sahani
Department of Master of Computer Application,
JCEI’s Jaihind Institute of Management and Research, Vadgaon Sahani
Every year, college offices answer the same questions from students and parents about admissions, fees, courses, eligibility, scholarships, hostels, examinations and contact details. Handling these by hand takes up staff time, is possible only in office hours, and does not always give the same answer twice. In this work we build a college enquiry chatbot that reads a question written in ordinary language and returns the best matching answer from a college knowledge base. The system is written in Python with scikit-learn and a small rule-based text normalizer, and users reach it through a simple Flask chat page. Each question is cleaned, tokenized, lemmatized and turned into a TF-IDF vector. A Logistic Regression classifier predicts the topic of the question, and cosine similarity then picks the closest stored question within that topic. When the classifier is not confident enough, the bot gives a fallback reply instead of guessing. We tested the system on a dataset prepared for this study, with 270 questions in 9 intents and 40 out-of-scope questions, over five random splits. It reached an intent accuracy of 84.4% and a weighted F1-score of 84.3%, against 59.6% for a retrieval-only baseline. It declined 83.2% of the out-of-scope questions and needed about 1.4 ms per query. The whole system runs on an ordinary computer with no GPU or paid service, and it can later be extended with deep learning models, more languages, or voice and mobile interfaces.
KEYWORDS
This paper presented a college enquiry chatbot that answers common student and parent questions in natural language using text pre-processing, TF-IDF features, intent classification and cosine-similarity retrieval. On our study dataset it reached 84.4% intent accuracy and declined 83.2% of out-of-scope questions, and the confidence threshold let it refuse instead of answering wrongly. The system runs on ordinary hardware and uses a knowledge base that staff can edit, so it can reduce the repetitive workload of the college office and give users quick, consistent replies.
[1] J. Weizenbaum, “ELIZA — A Computer Program for the Study ofNatural Language Communication Between Man and Machine,” Communications of the ACM, vol. 9, no. 1, pp. 36–45, 1966. [2] E. Adamopoulou and L. Moussiades, “Chatbots: History,Technology, and Applications,” Machine Learning with Applications, vol. 2, Art. no. 100006, 2020. [3] B. A. Shawar and E. Atwell, “Chatbots: Are They Really Useful?,”LDV Forum, vol. 22, no. 1, pp. 29–49, 2007. [4] C. D. Manning, P. Raghavan, and H. Schütze, Introduction to Information Retrieval. Cambridge, U.K.: Cambridge University Press, 2008. [5] S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python. Sebastopol, CA, USA: O’Reilly Media, 2009. [6] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,”Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [7] D. Jurafsky and J. H. Martin, Speech and Language Processing, 3rd ed. (draft). Stanford University, 2023. [Online]. https://web.stanford.edu/~jurafsky/slp3/ [8] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” in Proc. NAACL-HLT, 2019, pp. 4171–4186. [9] T. Bocklisch, J. Faulkner, N. Pawlowski, and A. Nichol, “Rasa: Open Source Language Understanding and Dialogue Management,” arXiv:1712.05181, 2017. [10] Python Software Foundation, “Python Documentation.” [Online]. https://docs.python.org/3/ [11] Pallets, “Flask Documentation.” [Online]. https://flask.palletsprojects.com/
Publication Date
10/31/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
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...