Development of OpenAI API Based Chatbot to Improve User Interaction on the JBMS Website
Gerald Santoso, Johan Setiawan, Agus Sulaiman
Abstract
This study presents an innovative chatbot, powered by OpenAI API, designed to enhance the user experience on the Journal of Business, Management, and Social Studies (JBMS) website. Chatbots have gained prominence for improving online interactions and information retrieval. The chatbot's development followed a structured prototype methodology, including Requirement Gathering, Prototype Building, Requirement Refinement, Customer Evaluation, and Design and Implementation. User Acceptance Testing (UAT) scored an average of 4.14, signifying high user satisfaction. UAT results showed positive user experiences and satisfaction with the chatbot. Integration of OpenAI API improved information extraction from journal articles and personalized article recommendations. Stakeholder feedback from JBMS's CEO, students, and UMN lecturers affirmed high satisfaction levels. Future research will refine the chatbot's features to align better with user needs, solidifying its role as an innovative tool for information retrieval within JBMS, and enhancing user service.