Loading...
Paper Type
ERF
Paper Number
1270
Description
Artificial Intelligence is increasingly driven by powerful but often opaque machine learning algorithms. These black-box algorithms achieve high performance but are not explainable to humans in a systematic and interpretable manner, a challenge known as Explainable AI (XAI). Informed by a synthesis of two converging literature streams on information systems development and psychology, we propose a new XAI approach termed Basic Explainable AI and a subsequent research agenda. We propose four research directions that focus on providing explanations by proactively considering the target audience's mental models and making the explanations maximally accessible to heterogeneous nonexpert users.
Recommended Citation
Lukyanenko, Roman; Castellanos, Arturo; Samuel, Binny; Tremblay, Monica; and Maass, Wolfgang, "Research Agenda for Basic Explainable AI" (2021). AMCIS 2021 Proceedings. 7.
https://aisel.aisnet.org/amcis2021/art_intel_sem_tech_intelligent_systems/art_intel_sem_tech_intelligent_systems/7
Research Agenda for Basic Explainable AI
Artificial Intelligence is increasingly driven by powerful but often opaque machine learning algorithms. These black-box algorithms achieve high performance but are not explainable to humans in a systematic and interpretable manner, a challenge known as Explainable AI (XAI). Informed by a synthesis of two converging literature streams on information systems development and psychology, we propose a new XAI approach termed Basic Explainable AI and a subsequent research agenda. We propose four research directions that focus on providing explanations by proactively considering the target audience's mental models and making the explanations maximally accessible to heterogeneous nonexpert users.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.