Survey of Chatbot Testing Methods on Social Media to Measure Accuracy

Abstract

The design of Chatbot aims to facilitate social activities in all areas to be considered. A Chatbot is one type of machine that can communicate with humans using natural language. Chatting is used to communicate, and it is a written conversation. Chatbot is a form of application implementation Natural Language Processing (NLP) that belongs to one branch of artificial intelligence or Artificial Intelligent AI social media now provides a service that allows developers to process and integrate chatbot applications. This paper aims to review the papers that build chatbot applications for various social media using various testing methods. The contribution to this paper is to determine which method can measure the level of chatbot accuracy best. This review paper will choose the equations of the most widely used test methods and social media from various papers, so that further research is expected to implement the right testing methods and use better social media in terms of user experience, features, and services. According to the review papers and papers, the Black-box and System Usability Scale testing methods are the most commonly used in the review papers. This testing method is a type of method that performs testing for the flow and how the chatbot works to achieve functional validation completely.