How to explain AI systems to end users: a systematic literature review and research agenda

Samuli Laato, Miika Tiainen, A. K.M. Najmul Islam, Matti Mäntymäki

Research output: Contribution to journalReview Articlepeer-review

21 Downloads (Pure)

Abstract

Purpose: Inscrutable machine learning (ML) models are part of increasingly many information systems. Understanding how these models behave, and what their output is based on, is a challenge for developers let alone non-technical end users. Design/methodology/approach: The authors investigate how AI systems and their decisions ought to be explained for end users through a systematic literature review. Findings: The authors’ synthesis of the literature suggests that AI system communication for end users has five high-level goals: (1) understandability, (2) trustworthiness, (3) transparency, (4) controllability and (5) fairness. The authors identified several design recommendations, such as offering personalized and on-demand explanations and focusing on the explainability of key functionalities instead of aiming to explain the whole system. There exists multiple trade-offs in AI system explanations, and there is no single best solution that fits all cases. Research limitations/implications: Based on the synthesis, the authors provide a design framework for explaining AI systems to end users. The study contributes to the work on AI governance by suggesting guidelines on how to make AI systems more understandable, fair, trustworthy, controllable and transparent. Originality/value: This literature review brings together the literature on AI system communication and explainable AI (XAI) for end users. Building on previous academic literature on the topic, it provides synthesized insights, design recommendations and future research agenda.

Original languageEnglish
Pages (from-to)1-31
Number of pages31
JournalINTERNET RESEARCH
Volume32
Issue number7
DOIs
Publication statusPublished - 2 May 2022
Publication typeA2 Review article in a scientific journal

Keywords

  • End users
  • Explainable AI
  • Explanatory AI
  • Human–computer interaction
  • Literature review
  • Machine learning
  • Systematic literature review
  • XAI

Publication forum classification

  • Publication forum level 2

ASJC Scopus subject areas

  • Communication
  • Sociology and Political Science
  • Economics and Econometrics

Fingerprint

Dive into the research topics of 'How to explain AI systems to end users: a systematic literature review and research agenda'. Together they form a unique fingerprint.

Cite this