<![CDATA[Demand for accurate information services, and responsiveness is increasing in the modern era, especially in the process of receiving new students. The limitations of human resources that provide information services in a direct way cause user delays and dissatisfaction. Therefore, an automatic solution that can provide efficient and effective information services, is the chatbot service (PMB) using AI to make it easier for prospective students and educational institutions to communicate. The study created a chatbot that could understand a better natural language by combining the neural convolutional network (CNN) and long short-term memory (LSTM) supported by embedding gloves. To ensure that the neural network's models can process text optimally, development processes involve important stages such as tokenization, padding, and the formation of the embedding matrix. Test results show that models have high training accuracy, but validation charts show overfitting, which is indicated by the big difference between losing training and losing validation. Embedding gloves, however, successfully enhance word representation and help people better understand the context of the text included. The CNN-LSTM PMB chatbot aims to provide a faster, more, relevant, and accurate service to prospective students]]>
Copyrights © 2024
