Research on Explainable Artificial Intelligence Techniques: An User Perspective
Fabio Daudt, Daniel Cinalli, Ana Cristina Bicharra García · 2021
Artificial intelligence (AI) has become part of our daily lives and is commonly used in a wide range of industries. However, most of users have little visibility and knowledge about how AI systems reach a particular decision and their outcomes in the various fields where AI and machine learning are being applied. Many of the algorithms' results cannot be understood and explained in terms of how and why a specific decision was taken. With the advance of artificial intelligence researches, several techniques and approaches have emerged over the last few years, but only a few studies have been produced with regards to the end-user perspective and comprehension of the algorithms outcomes. This paper aims to evaluate the comprehensibility of the explanations from the perspective of the different types of users, aiming to generate confidence and understanding of the results produced by the AI.