A Multi-Lingual Conversational AI Chatbot for Effective Educational Consultations: A Study of ACE-DS, University of Rwanda

Abstract

The demand for real-time consultation services from organizations is increasing, leading to prolonged waiting times, primarily due to limited opportunities for face-to-face interactions and language barriers. This study addresses this challenge by leveraging Artificial Intelligence (AI), Natural Language Processing (NLP), and linguistic technologies to develop a multilingual conversational AI Chabot for managing educational consultation services, using the African Center of Excellence in Data Science (ACE-DS), University of Rwanda, as a case study. Information and frequently asked questions (FAQs) about ACE-DS were used to train a Deep Learning Gated Recurrent Units (GRUs) algorithm to power the Chabot. Language detection and translation APIs were integrated to facilitate seamless multilingual conversations. The result of user survey conducted revealed that over 60% of respondents expressed high satisfaction with the Chabot’s performance including grammar, efficiency, language preferences, and response quality. This study showcases the potential of AI particularly NLP in enhancing educational consultation services, providing a framework for efficient information acquisition.