Science Communications for Explainable Artificial Intelligence

TL;DR

This paper proposes a framework based on Science Communications models to improve AI explanations, making them more effective for diverse users and enhancing AI literacy through better communication strategies.

Contribution

It introduces a novel framework adapting Science Communications models to XAI, aiming to improve user understanding and engagement with AI explanations.

Findings

Framework helps practitioners tailor AI explanations to different audiences

Improves user understanding of AI through adapted communication strategies

Supports development of more user-adaptive XAI systems

Abstract

Artificial Intelligence (AI) has a communication problem. XAI methods have been used to make AI more understandable and helped resolve some of the transparency issues that inhibit AI's broader usability. However, user evaluation studies reveal that the often numerical explanations provided by XAI methods have not always been effective for many types of users of AI systems. This article aims to adapt the major communications models from Science Communications into a framework for practitioners to understand, influence, and integrate the context of audiences both for their communications supporting AI literacy in the public and in designing XAI systems that are more adaptive to different users.