<![CDATA[Chatbot Questions and Answer (Q&A) has become a very important tool for companies to provide fast and effective customer support and service. However, the main challenge in the development of Chatbot Q&A is to ensure that the chatbot can understand the user's natural language and provide the right answers. In this research, Text Mining and Natural Language Processing (NLP) methods are applied to the Q&A Chatbot for PT PLN (Persero) South Sumatra region with the aim of improving the chatbot's ability to understand customer questions and provide accurate answers. The application designed in this study uses the software development method, namely the Rational Unified Process (RUP) model and is implemented into the Android operating system. As for testing using the Root Mean Square Error (RMSE) calculation. The accuracy of the test is indicated by the RMSE results having a small value (close to zero). From the results of testing sample data of 20 questions, the RMSE calculation value is 0.10, so it can be concluded that the prediction accuracy level in the text mining process in the application is very good (RMSE is close to 0). The result of this research is a tool in the form of an interactive information question and answer application like a discussion model and can use everyday language]]>
Copyrights © 2024
