Explainable Artificial Intelligence (XAI) from a user perspective- A synthesis of prior literature and problematizing avenues for future research

TL;DR

This paper synthesizes existing literature on Explainable AI from a user perspective, identifying key dimensions of explanations and effects, and proposes future research directions and a comprehensive framework for understanding XAI's impact on users.

Contribution

It provides a systematic review of XAI literature, identifies core explanation dimensions and effects, and develops a framework linking explanations to user behavior and future research avenues.

Findings

Four explanation dimensions: format, completeness, accuracy, currency.

Five effects of XAI: trust, transparency, understandability, usability, fairness.

Proposes a future research agenda and a comprehensive XAI framework.

Abstract

The final search query for the Systematic Literature Review (SLR) was conducted on 15th July 2022. Initially, we extracted 1707 journal and conference articles from the Scopus and Web of Science databases. Inclusion and exclusion criteria were then applied, and 58 articles were selected for the SLR. The findings show four dimensions that shape the AI explanation, which are format (explanation representation format), completeness (explanation should contain all required information, including the supplementary information), accuracy (information regarding the accuracy of the explanation), and currency (explanation should contain recent information). Moreover, along with the automatic representation of the explanation, the users can request additional information if needed. We have also found five dimensions of XAI effects: trust, transparency, understandability, usability, and fairness. In addition, we investigated current knowledge from selected articles to problematize future research agendas as research questions along with possible research paths. Consequently, a comprehensive framework of XAI and its possible effects on user behavior has been developed.