Talking Machine: A Survey of Chatbot Foundation, Use Case, and Challenges

Abstract

Recently, chatbot systems have grown from the very basic rule-based systems to more advanced ones, such as natural and context-aware systems that incorporate sophisticated neural network techniques. This paper provides a comprehensive review of evolution and taxonomy and analyzes the application of chatbots in various fields, such as healthcare, banking, education, mental health, customer service, and image recognition, to reveal contemporary strengths and applications. In addition to observation of the most important assessment measurements and highlights of the latest studies, promising performance has been reported in the literature, with accuracy/success rates over 90% for some studies, with user satisfaction levels reaching 95% in certain health-related scenarios; however, these results remain specific to their settings rather than generalizable for all chat applications. The paper concludes that contemporary AI-based chatbots are strong in response generation and context appreciation but are still weak when dealing with ambiguous questions and multi-turn dialogues. Some of the key challenges, such as making the system scalable and personal and achieving human-like conversational quality in different contexts, were identified. This in-depth review summarizes recent developments as well as challenges in the area of chatbot technology and emphasizes the necessity of innovation in AI and NLP to overcome these challenges and improve chatbot performance and user experience.

Ähnliche Arbeiten