Interacting with Explanations through Critiquing

TL;DR

This paper introduces a novel system that enables users to critique and modify recommendations through textual explanations, improving personalization and user trust in recommendation systems.

Contribution

It presents an innovative unsupervised critiquing method that allows interactive, multi-step preference adjustments based on textual explanations, enhancing recommendation adaptation.

Findings

Users prefer explanations generated by the new method over existing techniques.

The system effectively adapts to multi-step user critiques in real-world datasets.

It demonstrates significant improvements in recommendation personalization through interaction.

Abstract

Using personalized explanations to support recommendations has been shown to increase trust and perceived quality. However, to actually obtain better recommendations, there needs to be a means for users to modify the recommendation criteria by interacting with the explanation. We present a novel technique using aspect markers that learns to generate personalized explanations of recommendations from review texts, and we show that human users significantly prefer these explanations over those produced by state-of-the-art techniques. Our work's most important innovation is that it allows users to react to a recommendation by critiquing the textual explanation: removing (symmetrically adding) certain aspects they dislike or that are no longer relevant (symmetrically that are of interest). The system updates its user model and the resulting recommendations according to the critique. This is based on a novel unsupervised critiquing method for single- and multi-step critiquing with textual explanations. Experiments on two real-world datasets show that our system is the first to achieve good performance in adapting to the preferences expressed in multi-step critiquing.