Human-Centered Explainability in Interactive Information Systems: A Survey

TL;DR

This survey reviews recent research on human-centered explainability in interactive information systems, highlighting conceptual frameworks, explanation designs, and evaluation methods to improve system transparency and user trust.

Contribution

It provides a comprehensive classification of explainability concepts, explanation designs, and measurement approaches, guiding future research and development in human-centered AI explanations.

Findings

Identified five key dimensions of explainability

Developed a classification scheme for explanation designs

Categorized explainability measurements into six user-centered dimensions

Abstract

Human-centered explainability has become a critical foundation for the responsible development of interactive information systems, where users must be able to understand, interpret, and scrutinize AI-driven outputs to make informed decisions. This systematic survey of literature aims to characterize recent progress in user studies on explainability in interactive information systems by reviewing how explainability has been conceptualized, designed, and evaluated in practice. Following PRISMA guidelines, eight academic databases were searched, and 100 relevant articles were identified. A structural encoding approach was then utilized to extract and synthesize insights from these articles. The main contributions include 1) five dimensions that researchers have used to conceptualize explainability; 2) a classification scheme of explanation designs; 3) a categorization of explainability measurements into six user-centered dimensions. The review concludes by reflecting on ongoing challenges and providing recommendations for future exploration of related issues. The findings shed light on the theoretical foundations of human-centered explainability, informing the design of interactive information systems that better align with diverse user needs and promoting the development of systems that are transparent, trustworthy, and accountable.