In Conversational Recommender Systems (CRS), an extensive and meticulous analysis of previous scholarly works, publications, and studies is essential for developing a thorough grasp of knowledge, spotting research gaps, and laying the groundwork for future research projects. To ensure a focused review, researchers are undertaking a literature survey to define the scope of their required study, identifying important research areas and goals. Following this, finding knowledge gaps and unresolved issues is a key objective of a literature review since it helps to shape the creation of novel research questions and goals.
CRS is an interesting and exciting area of research and application in artificial intelligence and recommender systems because it can completely change how users find and interact with products, services, and content. CRS is predicted to become indispensable in several industries, including e-commerce, healthcare, and customer service, by offering tailored recommendations through natural language interactions that are dynamic in turn, improve user satisfaction and engagement. Using sophisticated natural language processing (NLP) models became a prominent trend that greatly enhanced the comprehension of user queries and context, enabling more complex and context-aware recommendations.