Fairness, explainability and in‑between: understanding the impact of different explanation methods on non‑expert users perceptions of fairness toward an algorithmic system: A seminar by Prof. Trsvi Kuflik


In the context of an Erasmus+ International Mobility Programme, Dr. Tsvi Kuflik, Professor of Information Systems at the University of Haifa, visited the Open University of Cyprus (OUC) for a weekly series of seminars. On the 19th of June 2023, in collaboration with the Cyprus Center for Algorithmic Transparency (CyCAT), the OUC hosted his hybrid open seminar entitled “Fairness, explainability and in‑between: understanding the impact of different explanation methods on non‑expert users perceptions of fairness toward an algorithmic system”.

 

Abstract: In light of the widespread use of algorithmic (intelligent) systems across numerous domains, there is an increasing awareness about the need to explain their underlying decision-making process and resulting outcomes. Often, these systems are being considered as black boxes, and adding explanations to their outcomes may contribute to the perception of their transparency, resulting to an increase in users’ trust and fairness perception towards the system. Different explanation styles may have a different impact on users’ perception of fairness towards any systems and on their understanding of the outcome of the system. Hence, there is a need to understand how various explanation styles may impact non-expert users’ perceptions of fairness and understanding of the system’s outcome. In this seminar, Professor Kuflik presents a recent study which aimed at fulfilling this need. His research team performed a between-subject user study to examine the effect of various explanation styles on users’ fairness perception and understanding of the outcome. The results suggest a) that providing some kind of explanation contributes to users’ understanding of the outcome and that some explanation styles are more beneficial than others, and b) shed light on one of the main problems in explainability of algorithmic systems, which is choosing the best explanation to promote users’ fairness perception towards a particular system, with respect to the outcome of the system.

 


19 June 2023 5:00 pm (GMT)

Online