An inquiry smart chatbot system for Al-Zaytoonah University of Jordan

Abstract

Chatbots are important in artificial intelligence (AI) and natural language processing (NLP). The development of the chatbot is viewed as a continuous issue in the field. This is suitable for Arabic chatbots that are not widely available. This study aims to fill the gap in Arabic chatbot development by creating an Arabic chatbot system for university admissions. The system uses a deep neural network model and a manually constructed dataset for conversation pairings, utilizing the Jordanian Arabic dialect from Al-Zaytoonah University of Jordan’s (ZUJ) website. The system efficiently answers most user queries, improving the counseling experience and reducing workload in the admissions department. The adoption of this system also minimizes website traffic congestion. The study contributes to the improvement of Arabic chatbot technology by creating a deep learning-based system optimized for university admissions, demonstrating its potential impact in the Arabic-speaking context. Future research can further enhance the system’s capabilities and its applicability in other disciplines.