Abstract
First-year students and visitors to South African universities often lose their way. This is due to widespread areas and complex routes or pathways on campuses. The experience can be intimidating and confusing to students and visitors who ask for directions from senior students or university personnel at helpdesks. This paper presents a potential answer to this dilemma – a hybrid chatbot system named SoshaMapBot. This chatbot was developed and tested on the Soshanguve campus of the Tshwane University of Technology in South Africa. The SoshaMapBot uses the entity recognition technique of natural language processing to process the written texts that the user types into the chatbot. The SoshaMapBot asks the users to upload photographs of their surroundings to the program via text. The chatbot then captures these images as inputs and returns textual responses with directions to the user. This study evaluated the proposed chatbot to confirm whether using image processing in chatbots is a viable and sustainable methodology. During the evaluation process of the developed chatbot, the researchers found that the developed chatbot exhibited a 75% accuracy rate in determining where the students or visitors find themselves on campus and giving the correct directions to them. The research found that image processing is a feasible way to develop chatbots and the findings are explained in this paper. However, image processing must be combined with the correct choice of technology, algorithms, and methodologies. Therefore, by developing this chatbot, this study contributes to communication technology for enhanced communication techniques.
Author Information
Goodman Dimo, Tshwane University of Technology, South Africa
Joey Jansen van Vuuren, Tshwane University of Technology, South Africa
Anna-Marie Jansen van Vuuren, Tshwane University of Technology, South Africa
Paper Information
Conference: MediAsia2022
Stream: Social Media and Communication Technology
This paper is part of the MediAsia2022 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window
To cite this article:
Dimo G., Vuuren J., & Vuuren A. (2022) Using a Smart Chatbot System as a Communication Tool for Campus Navigation ISSN: 2186-5906 – The Asian Conference on Media, Communication & Film 2022: Official Conference Proceedings https://doi.org/10.22492/issn.2186-5906.2022.12
To link to this article: https://doi.org/10.22492/issn.2186-5906.2022.12
Comments
Powered by WP LinkPress