This article is a tutorial introduction , it is recommended to read 5 minutes
In this tutorial, we will conduct a multi-faceted survey of existing research in the field of conversational recommender systems.
Personalized recommendations have become a ubiquitous part of our online user experience. Today, recommendations are typically implemented as a one-way communication from the system to the user. However, in recent years, we have seen an increasing interest in Conversational Recommender Systems (CRS). These systems are able to engage in an interactive dialogue with the user, usually using natural language, with the goal of providing appropriate recommendations based on the user's observed needs and preferences. Although conversational recommendation is not a new field, recent developments in natural language processing techniques and deep learning have significantly stimulated new research in this area.
In this tutorial, we will conduct a multi-faceted survey of existing research in the field of conversational recommender systems. We will first discuss the typical technical architecture and possible interaction modes of CRS. We will then focus on the various types of knowledge that these systems can rely on, and detail the computational tasks that these systems typically have to support. In the final part of this tutorial, we will highlight current approaches and the open challenges faced when evaluating complex interactive software solutions such as conversational recommender systems.
https://web-ainf.aau.at/pub/jannach/files/ijcai-2022/crs-tutorial-2022.html
