Research Cell: An International Journal of Engineering Sciences

Open Access Open Access  Restricted Access Subscription Access

KU BOT: An NLP-Powered Chatbot for University of Kerala Admission


Affiliations
1 Department of Futures Studies, University of Kerala, Trivandrum, Kerala, India - 680567., India
2 Professor & HOD, Dept of CSE, ICCS College of Engineering and Management, Kerala., India
 

This research focuses on the use of AI-powered chatbots in customer interactions for business growth and task automation. The study uses the KU-BOT, a chatbot developed for automating the admission process at the University of Kerala, as a case study. The KU-BOT addresses student queries, provide quick responses and passes more complicated ones to human representatives. The study uses the RASA open-source framework with an accuracy rate of 98.25%. The research highlights the benefits of implementing chatbots in academic institutions, including increased productivity, improved customer satisfaction, and reduced operational costs. Chatbots can also serve as a valuable resource for students, providing access to information and resources around the clock. The study provides guidelines for building AI-driven chatbots in academic institutions, including the use of NLP and ML techniques. In conclusion, chatbots can be a valuable asset in improving communication and providing information when used as a complementary tool to human interaction.

Keywords

Rasa, NLP, ML, Chatbot.
User
Notifications
Font Size

  • Faulkner, J., Pawlowski, N., & Nichol, A. (2017). "Rasa: Open Source Language Understanding and Dialogue Management." Preprint arXiv:1712.05181

  • X. Kong, G. Wang, and A. Nichol, Conversational AI With Rasa: Build, Test, Deploy AIPowered, Enterprise-Grade Virtual Assistants Chatbots. Birmingham, U.K.: Packt, 2021.

  • Y. Mellah, T. Bouchentouf, N. Rahmoun, and M. Rahmoun, ‘‘Bilingual chatbot for Covid-19 detection based on symptoms using rasa NLU,’’ in Proc. 2nd Int. Conf. Innov. Res. Appl. Sci., Eng. Technol. (IRASET), Mar. 2022, pp. 1–5.

  • W. Astuti, D. P. I. Putri, A. P. Wibawa, Y. Salim, Purnawansyah, and A. Ghosh, ‘‘Predicting frequently asked questions (FAQs) on the COVID19 chatbot using the DIET classifier,’’ in Proc. 3rd East Indonesia Conf. Comput. Inf. Technol. (EIConCIT), Apr. 2021, pp. 25–29.

  • L. Fauzia, R. B. Hadiprakoso, and Girinoto, ‘‘Implementation of chatbot on university website using RASA framework,’’ in Proc. 4th Int. Seminar Res. Inf. Technol. Intell. Syst. (ISRITI), Dec. 2021, pp. 373–378.

  • M.-T. Nguyen, M. Tran-Tien, A. P. Viet, H.-T. Vu, and V.-H. Nguyen, ‘‘Building a chatbot for supporting the admission of universities,’’ in Proc. 13th Int. Conf. Knowl. Syst. Eng. (KSE), Nov. 2021, pp. 1–6.

  • T. Bunk, D. Varshneya, V. Vlasov, and A. Nichol, ‘‘DIET: Lightweight language understanding for dialogue systems,’’ 2020, arXiv:2004.09936.

  • J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, ‘‘BERT: Pre-training of deep bidirectional transformers for language understanding,’’ 2018, arXiv:1810.04805.

  • J. Pennington, R. Socher, and C. D. Manning, ‘‘GloVe: Global vectors for word representation,’’ in Proc. 2014 Conf. Empirical Methods Natural Lang. Process. (EMNLP), 2014, pp. 1532–1543.

  • M. Henderson, I. Casanueva, N. Mrkšić, P.-H. Su, T.-H. Wen, and I. Vulić, ‘‘ConveRT: Efficient and accurate conversational representations from transformers,’’ 2019, arXiv:1911.03688.

  • M. Arevalillo-Herráez, P. Arnau-González, I. Bravo-Cabrera, and N. Ramzan, ‘‘On using the diet architecture for sentiment analysis and emotion detection,’’ in Proc. Int. Workshop Affect. Comput. Emotion Recognit., 21st IEEE/WIC/ACM Int. Conf. Web Intell. Intell. Agent Technol., Niagara Falls, NY, USA, Nov. 2022, pp. 1–5. [Online]. Available: https://www.wi-iat.com/wiiat2022/Workshops-Special-Sessions.html

  • E. Frank, M. A. Hall, and I. H. Witten, Data Mining: Practical Machine Learning Tools and Techniques, 4th ed. Berlin, Germany: Morgan Kaufmann, 2016.

  • M. R. Berthold, N. Cebron, F. Dill, T. R. Gabriel, T. Kötter, T. Meinl, P. Ohl, C. Sieb, K. Thiel, and B. Wiswedel, ‘‘KNIME: The Konstanz information miner,’’ in Data Analysis, Machine Learning and Applications, C. Preisach, H. Burkhardt, L. Schmidt-Thieme, and R. Decker, Eds. Berlin, Germany: Springer, 2008, pp. 319–326.

  • D. Merlini and M. Rossini, ‘‘Text categorization with WEKA: A survey,’’ Mach. Learn. Appl., vol. 4, Jun. 2021, Art. no. 100033.

  • Windiatmoko, Y., et al. (2021). "Developing Facebook Chatbot Based on Deep Learning Using RASA Framework for University Enquiries." IOP Conf. Ser.: Mater. Sci. Eng. 1077 012060

  • Merisalo, S. (2018). "Developing a Chatbot for Customer Service to Metropolia UAS Student Affairs Office." (Helsinki Metropolia University of Applied Sciences)

  • Brennan, S., & Fung, K. (2018). "Chatbots in Healthcare: A Review of Current Applications and Future Possibilities." Journal of Medical Internet Research, 20(5). doi:10.2196/jmir.9758

  • Dormehl, L. (2017). "The History of Chatbots: From ELIZA to Siri." Digital Trends. Retrieved from https://www.digitaltrends.com/cool-tech/history-of-chatbots/

  • KPMG. (2017). "The Rise of the Chatbot: How AI is Transforming Customer Service." KPMG. https://www.kpmg.com/us/en/insights/articles/2017/05/rise-of-the-chatbot.html

  • Sage, A. (2014). "A Brief History of Chatbots." Creative Bloq. Retrieved from https://www.creativebloq.com/features/a-brief-history-of-chatbots

  • Vandenbosch, B., & De Ruyter, K. (2016). "Chatbots in Customer Service: An Exploratory Study." Journal of Business Research, 69(12), 5657-5666. doi:10.1016/j.jbusres.

  • Rasa. (n.d.). "Rasa: Open Source Conversational AI." Retrieved from https://rasa.com/

  • Bocklisch, C., Rössler, A., & Ziegler, M. (2017, November 9). "Rasa: A New Way of Building Chatbots." (https://blog.rasa.com/rasa-a-new-way-of-building-chatbots/(

  • "The Effects of Using Chatbots in Language Learning: A Review." Computers & Education, 123, 11-21. (https://www.sciencedirect.com/science/article/pii/S0360131518301101)

  • "Chatbot-based Research: An Overview and Future Directions." International Journal of Human-Computer Studies, 104, 37-52. (https://www.sciencedirect.com/science/article/pii/S1071581917301534)

  • "Chatbots in Higher Education: A Review of Applications and Implications." Interactive Learning Environments, 27(6), 977-994. (https://www.tandfonline.com/doi/abs/10.1080/10494820.2018.1501656)


Abstract Views: 67

PDF Views: 0




  • KU BOT: An NLP-Powered Chatbot for University of Kerala Admission

Abstract Views: 67  |  PDF Views: 0

Authors

Midhun Das L
Department of Futures Studies, University of Kerala, Trivandrum, Kerala, India - 680567., India
Prem Sankar C
Professor & HOD, Dept of CSE, ICCS College of Engineering and Management, Kerala., India

Abstract


This research focuses on the use of AI-powered chatbots in customer interactions for business growth and task automation. The study uses the KU-BOT, a chatbot developed for automating the admission process at the University of Kerala, as a case study. The KU-BOT addresses student queries, provide quick responses and passes more complicated ones to human representatives. The study uses the RASA open-source framework with an accuracy rate of 98.25%. The research highlights the benefits of implementing chatbots in academic institutions, including increased productivity, improved customer satisfaction, and reduced operational costs. Chatbots can also serve as a valuable resource for students, providing access to information and resources around the clock. The study provides guidelines for building AI-driven chatbots in academic institutions, including the use of NLP and ML techniques. In conclusion, chatbots can be a valuable asset in improving communication and providing information when used as a complementary tool to human interaction.

Keywords


Rasa, NLP, ML, Chatbot.

References