Revolutionizing Journal Publishing: Unleashing The Power Of Web-Based Chatbot Development With Dialogflow And Natural Language Processing

Abstract

The chatbot is a manifestation of Artificial Intelligence that can replace humans in engaging in conversational interactions and providing information services to users or visitors. Chatbots generally interact through text messages, voice, images, and other mediums. In this study, a web-based chatbot application was developed for a journal website called the Journal of Multidisciplinary Issues, aiming to relieve site administrators from having to repeatedly answer the same visitor questions. The development of the chatbot application followed the Rapid Application Development method, involving several stages including planning, design, system development, implementation, and testing. The application was built using Google Dialogflow services, employing Natural Language Processing techniques, along with the integration feature called Dialogflow Messenger, which offers a wide range of response options for journal websites utilizing Open Journal Systems. The chatbot application was evaluated using Alpha and Closed Beta Testing methodologies, which yielded promising results. The chatbot demonstrated the ability to provide appropriate responses after being tested with various question scenarios, achieving a score of 85.25% in the questionnaire-based assessment, which aimed to gauge visitor perspectives on the developed chatbot application. Future research endeavors should focus on integrating the chatbot with popular social media platforms such as Facebook, WhatsApp, or LINE.