Developing Facebook Chatbot Based on Deep Learning Using RASA Framework for University Enquiries

Abstract

Smart systems for universities powered by artificial intelligence have been massively developed to help humans in various tasks. The chatbot concept is not something new in today’s society which is developing with recent technology. College students or candidates of college students often need actual information like asking for something to customer service, especially during this pandemic, when it is difficult to have an immediate face-to-face meeting. Chatbots are functionally helping in several things such as curriculum information, admission for new students, schedule info for any lecture courses, students grade information, and some adding features for Muslim worships schedule, also weather forecast information. This Chatbot is developed by deep learning models, which was adopted by an artificial intelligence model that replicates human intelligence with some specific training schemes. This kind of deep learning is based on RNN which has some specific memory savings scheme for the deep learning model, specifically this chatbot using LSTM which already integrates by RASA framework. LSTM is also known as Long Short Term Memory which efficiently saves some required memory but will remove some memory that is not needed. This Chatbot uses the Facebook platform because the Facebook users have already reached up to 60.8% of its entire population in Indonesia.

Building a Machine Learning Powered Chatbot for KSU Blackboard Users

“…Another study for developing a chatbot for university inquiries was put forward by [24]. This study discussed the development of a deep-learning based chatbot using RASA framework.…”

The Barcelona Conference on Education 2022: Official Conference Proceedings

“…An intelligent assistant can take on different forms. However, in general, the term describes an artificial intelligence system that can use natural language in communicating with users (Windiatmoko et al, 2021). While most of the assistants focus on communication components in the form of chatbots, they can also include other applications such as peer support modules, content quizzes, or recommender modules (Song et al, 2019, Schurz et al, 2021.…”

Proceedings - 4th International Conference Business Meets Technology 2022

“…Universities expect the offer of such systems, especially due to the growing use of distance learning settings, to improve communication and the general learning experience between lecturers and students as well as to provide administrative support (Song et al, 2019). In general, an intelligent assistant can be understood as an AI system that is capable of conversing with users in natural language (Windiatmoko et al, 2020). They can respond to instructions and complete certain tasks or answer queries by finding and providing information (Chandraa & Suyanto, 2019).…”

“…The majority of assistants focus on the communication components, which means that there are numerous chatbots that only focus on providing information by answering questions about various topics like application deadlines, exam results or general information about the university [e.g. Windiatmoko et al, 2020;Chandraa & Suyanto, 2019;Ranoliya et al, 2017). These systems require large amounts of data, which are available e.g.…”

“…An intelligent assistant can be defined as an artificial intelligence system which is capable of talking to users in natural language (Windiatmoko, Rahmadi & Hidayatullah, 2021). They are able to respond to instructions and to help with certain tasks or queries by finding and providing information (Chandra & Suyanto, 2019).…”