Explaining compound critiques

doi:10.1007/s10462-005-4614-8

2005-10-01

PRE

DOI：10.1007/s10462-005-4614-8

原文链接

原文求助

摘要

En 中文

When it comes to buying expensive goods people expect to be skillfully steered through the options by well-informed sales assistants who are capable of balancing the user's many and varied requirements. In addition users often need to be educated about the product space, especially if they are to come to understand what is available and why certain options are being recommended by the sales-assistant. It is now well accepted that interactive recommender systems, the on-line equivalent of a sales assistant, also need to educate users about the product space and to justify their recommendations. In this paper we focus on a novel approach to explanation. Instead of attempting to justify a particular recommendation we focus on how certain types of feedback can help users to understand the recommendation opportunities that remain if the current recommendation should not meet their requirements. Specifically, we describe how this approach to explanation is tightly coupled with the generation of compound critiques, which act as a form of feedback for users. Furthermore, we argue that these explanation-rich critiques have the potential to dramatically improve recommender performance and usability.

Keyword:

case-based reasoning

compound critiquing

explanation

feedback elicitation in recommender systems