Justification vs. Transparency: Why and How Visual Explanations in a Scientific Literature Recommender System

TL;DR

This paper explores the design and impact of visual explanations in a scientific literature recommender system, focusing on how justification and transparency influence user trust and satisfaction through a user-centered approach.

Contribution

It systematically analyzes the relationship between explanation types and goals, and demonstrates how tailored visual explanations affect user perceptions in explainable recommendation.

Findings

Different explanation types align with specific goals and user types.

Providing both Why and How explanations influences perceptions of transparency and trust.

Qualitative evidence supports tailored explanations improve user satisfaction.

Abstract

Significant attention has been paid to enhancing recommender systems (RS) with explanation facilities to help users make informed decisions and increase trust in and satisfaction with the RS. Justification and transparency represent two crucial goals in explainable recommendation. Different from transparency, which faithfully exposes the reasoning behind the recommendation mechanism, justification conveys a conceptual model that may differ from that of the underlying algorithm. An explanation is an answer to a question. In explainable recommendation, a user would want to ask questions (referred to as intelligibility types) to understand results given by the RS. In this paper, we identify relationships between Why and How explanation intelligibility types and the explanation goals of justification and transparency. We followed the Human-Centered Design (HCD) approach and leveraged the What-Why-How visualization framework to systematically design and implement Why and How visual explanations in the transparent Recommendation and Interest Modeling Application (RIMA). Furthermore, we conducted a qualitative user study (N=12) to investigate the potential effects of providing Why and How explanations together in an explainable RS on the users' perceptions regarding transparency, trust, and satisfaction. Our study showed qualitative evidence confirming that the choice of the explanation intelligibility types depends on the explanation goal and user type.