A Review of Existing Conversational Recommendation Systems

ChatGPT, Alexa, Siri, Okay Google are an indispensable part of our lives today. These assistants are referred to as Digital Assistants and enable users to communicate their choices through natural language. The Digital Assistants ease the customer task of selecting items in various applications like movies, songs and so on. This process of making a choice through natural language conversations is known as a Conversational Recommender system (CoRS). CoRS is a dialogue-based model which aims to provide customer with accurate and quality recommendations. The interaction-oriented method gives the customer an edge over the traditional way of seeking recommendations. The traditional recommendation systems are static in nature and derive information through past history of the customer. A CoRS mitigates the challenges faced in the earlier methods of recommendation like cold start where in a new user is often recommended inaccurate choices. Other issues like data sparsity and lack of diversity due to not so updated content to choose from are common. CoRS is dynamic in nature, it works on delivering high end choices by interpreting the customer demands one dialogue at a time. This comprehensive survey aims to give an overview of the research in progress using conversation as a means to achieve better results for recommendation systems.