Prestigious Women Researchers Lecture Series: 'Influence of context on users' views about explanations for decision-tree predictions'

This talk describes research where we consider the influence of two types of contextual information, background information available to users and users’ goals, on users’ views and preferences regarding explanations generated for the outcomes predicted by Decision Trees. To study the influence of background information, we generate contrastive explanations that address potential conflicts between aspects of Decision-Tree predictions and plausible expectations licensed by background information. To investigate the influence of users’ goals, we employ an interactive setting where given an initial explanation for a predicted outcome and a goal, users select follow-up questions, and assess the explanations that answer these questions. In this talk, I describe the algorithms that generate explanations for both situations, discuss the experiments conducted to evaluate our explanations, and present our main results.


Ingrid Zukerman is a Professor in the Department of Data Science and Artificial Intelligence in the Faculty of Information Technology at Monash University. She received her BSc degree in Industrial Engineering and Management and her MSc degree in Operations Research from the Technion – Israel Institute of Technology. She obtained her PhD in Computer Science from UCLA in 1986. Since then, she has been working in the Faculty of Information Technology at Monash University. Her areas of interest are explainable Artificial Intelligence (XAI), dialogue systems, trust in automated agents, and assistive systems for elderly and disabled people.

This 'Lecture' is part of the 'Prestigious Women Researchers Lecture Series'