Write a Blog >>
Tue 12 Oct 2021 15:30 - 15:40 - Visual Program and Information Representations (2) Chair(s): Thomas LaToza

The large-scale adoption of systems that automate classifications using Machine Learning (ML) algorithms to support or make decisions with profound consequences for human beings raises pressing challenges. It is important to understand how users’ trust is affected by ML models’ suggestions, even when they are wrong. Much of the research so far has focused on the user’s ability to interpret what a model has learned. In this work, we seek to understand another aspect of ML interpretability: how the presence of classification probabilities affect users’ trust in the model outcomes, especially in ambiguous scenarios. To this end, we conducted an online survey in which we asked participants to evaluate their agreement with an automatic classification made by an ML model before and after presenting them the model classification probabilities. Surprisingly, we found that, in ambiguous scenarios, respondents agreed more with incorrect model outcomes than with correct ones, requiring further analyses.

Tue 12 Oct

Displayed time zone: Central Time (US & Canada) change

15:30 - 16:10
Visual Program and Information Representations (2)Journal-First Presentations / Research Papers
Chair(s): Thomas LaToza George Mason University
15:30
10m
Paper
Exploring the impact of classification probabilities on users’ trust in ambiguous instancesFull paper
Research Papers
15:40
10m
Talk
An end-to-end model-based approach to support big data analytics developmentJournal-first
Journal-First Presentations
Hourieh Khalajzadeh Monash University, Australia, Anj Simmons Deakin University, Mohamed Abdelrazek Deakin University, Australia, John Grundy Monash University, John Hosking University of Auckland, Qiang He Swinburne University of Technology
15:50
10m
Talk
Run-time conflict detection in visual language parsingJournal-first
Journal-First Presentations
Gennaro Costagliola Università di Salerno, Vincenzo Deufemia University of Salerno, Filomena Ferrucci University of Salerno, Carmine Gravino University of Salerno
16:00
10m
Short-paper
Algot: An Educational Programming Language with Human-Intuitive Visual SyntaxShort paper
Research Papers
Sverrir Thorgeirsson ETH Zurich, Zhendong Su ETH Zurich