A Review on Chatur: Chatbot for College

Abstract

In today’s fast-paced college environment, students and faculty require timely access to accurate information on a variety of topics, such as admissions, course details, fees, and campus facilities. Traditional methods of information dissemination, such as websites, emails, and in-person consultations, often lead to delays and inefficiencies, causing frustration among users and increasing administrative workloads. To address this challenge, we developed Campus Query: A Q&A Chatbot for College, an intelligent conversational agent designed to provide real-time, accurate answers to frequently asked questions. This paper presents the design, development, and implementation of the chatbot, following a structured, two-phase approach. The initial phase employs a rule-based system, where the chatbot is programmed to handle common queries through predefined responses, keyword matching, and basic conversation flow. Although effective for standard queries, the limitations of this approach in handling more nuanced questions necessitated the transition to the second phase. In the second phase, we integrate the Rasa framework, which enhances the chatbot with natural language understanding (NLU), enabling it to recognize user intents, extract entities, and manage complex, multi-turn conversations. This phase introduces greater flexibility, allowing the chatbot to handle more varied user inputs and follow-up interactions in a conversational context. Through rigorous testing and user feedback, the chatbot has demonstrated its ability to improve information accessibility and alleviate the burden on administrative staff. By providing immediate responses to common queries, the chatbot enhances the overall user experience for students and faculty. Future enhancements will focus on incorporating more advanced features, such as dynamic content retrieval and further personalization, to expand the chatbot’s capabilities and adaptability. Chatbots have become an essential part of human-to-machine interactions, utilizing knowledge-based databases for improved conversational models. Deep learning techniques have been widely applied in IoT big data and streaming analytics to process large-scale data efficiently [1].

Introduction

The paper presents Campus Query, an intelligent Q&A chatbot designed to improve information accessibility and reduce administrative workload in college campuses. Traditionally, student and faculty queries on admissions, courses, fees, and facilities are handled through static methods like websites and emails, which can be slow and inefficient. Campus Query leverages advances in conversational AI and deep learning to provide instant, 24/7 responses.

The chatbot was developed in two phases:

• Phase 1: A rule-based system using keyword matching and predefined responses to answer frequent questions. This system was quick to deploy and effective for simple queries but lacked flexibility for complex or multi-turn conversations.

• Phase 2: Integration of the Rasa framework enabled advanced Natural Language Understanding (NLU), allowing the chatbot to recognize user intents, extract key entities, and handle dynamic, multi-turn dialogues. Custom actions allowed real-time data retrieval from college databases, enhancing response accuracy and relevance.

Implementation involved Python, Flask, PostgreSQL, and web technologies for the interface. The system evolved to better understand user queries, manage conversation context, and improve user interaction quality.

Evaluation results showed:

• Phase 1 had 95% accuracy on straightforward queries but limited flexibility.

• Phase 2 achieved 92% intent recognition accuracy, 90% entity extraction accuracy, and an overall user satisfaction rate of 80%, supporting more natural and context-aware interactions despite a slight increase in response time.

User feedback was incorporated for continuous improvement, making Campus Query a more intelligent, efficient, and user-friendly campus information tool.

Conclusion

The development of Campus Query: A Q&A Chatbot for College demonstrates the significant potential of intelligent chatbots to streamline communication and enhance information accessibility in higher education environments. Through a structured, two-phase approach—starting with a rule-based system and advancing to a more sophisticated NLU-powered chatbot using the Rasa framework—the project successfully addressed the primary challenges faced by students and faculty in accessing timely and accurate information. The chatbot was able to automate responses to frequently asked questions related to admissions, courses, fees, and campus facilities, reducing the workload on administrative staff and improving the user experience.

References

[1] M. Mohammadi, A. Al-Fuqaha, S. Sorour and M. Guizani, \"Deep Learning for IoT Big Data and Streaming Analytics: A Survey,\" in IEEE Communications Surveys & Tutorials, vol. 20, no. 4, pp. 2923-2960, Fourthquarter 2018. doi: 10.1109/COMST.2018.2844341. [2] Luckow, M. Cook, N. Ashcraft, E. Weill, E. Djerekarov and B. Vorster, \"Deep learning in the automotive industry: Applications and tools,\" 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, 2016, pp. 3759-3768. doi: 10.1109/BigData.2016.7841045. [3] Xiyang Song, Huangwei Fang, Xiong Jiao and Ying Wang, \"Autonomous mobile robot navigation using machine learning,\" 2012 IEEE 6th International Conference on Information and Automation for Sustainability, Beijing, 2012, pp. 135-140. doi: 10.1109/ICIAFS.2012.6419894. [4] Zelic, I. Kononenko, N. Lavrac and V. Vuga, \"Diagnosis of sport injuries with machine learning: explanation of induced decisions,\" Proceedings of Computer Based Medical Systems, Maribor, amritaSlovenia, 1997, pp. 195-199. doi: 10.1109/CBMS.1997.596433. [5] Setiaji and F. W. Wibowo, \"Chatbot Using a Knowledge in Database: Human-to-Machine Conversation Modeling,\" 2016 7th International Conference on Intelligent Systems, Modelling. [6] H. N. Io and C. B. Lee, \"Chatbots and conversational agents: A bibliometric analysis,\" 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, 2017, pp. 215-219. doi: 10.1109/IEEM.2017.8289883. [7] Yu Wang, \"A new concept using LSTM Neural Networks for dynamic system identification,\" 2017 American Control Conference (ACC), Seattle, WA, 2017, pp. 5324-5329. doi: 10.23919/ACC.2017.7963782. [8] J. Kim, J. Kim, H. L. T. Thu and H. Kim, \"Long Short-Term Memory Recurrent Neural Network Classifier for Intrusion Detection,\" 2016 International Conference on Platform Technology and Service (PlatCon), Jeju, 2016, pp. 1-5. doi: 10.1109/PlatCon.2016.7456805. [9] M, Akumar, and Dr. Soman K. P., “Amrita_CEN at SemEval-2016: Complex Word identification using word embeddings”, in International Workshop on Semantic Evaluation (SemEval 2016), 2016, 2016. [10] R. Vinayakumar, K. P. Soman and P. Poornachandran, \"Long short-term memory-based operation log anomaly detection,\" 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Udupi, 2017, pp. 236-242. doi: 10.1109/ICACCI.2017.8125846.

Copyright

Copyright © 2025 Prof. Gopika Fattepurkar, Prathamesh Govekar, Niranjan Khude, Aniket Pore, Gunjan Gandhi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.