To offer automatic online advice and help, chatbots are sophisticated conversational computer systems that resemble a human conversation. As chatbots' advantages grew, a variety of sectors began to use them extensively to give customers virtual support. Chatbots take advantage of methods and algorithms from two Artificial Intelligence areas: Machine Learning and Natural Language Processing. There are still several obstacles and restrictions to their use. In order to discover two NMT model variables' effects on chatbot performance, this paper does several experiments on a deep neural network chatbot model. Two straightforward and useful kinds of attentional mechanisms are used in this chatbot model: a local technique that only considers a small subset of source words at a time, as opposed to a global approach that always pays attention to all source words. This paper conducts experiments to examine how different model variables affect chatbot performance. This paper created a question template with eight general questions to test chatbot performance. Through the whole experiment results, increasing the number of iterations and increasing the dataset scale can improve the vocabulary and logic of the chatbot dialog to achieve better performance.