Gillies, Marco; Kleinsmith, Andrea and Brenton, Harry. 2015. 'Applying the CASSM Framework to Improving End User Debugging of Interactive Machine Learning'. In: ACM Intelligent User Interfaces (IUI). Atlanta, United States. [Conference or Workshop Item]

Preview

Text CASSMForEmbodiedInteraction_final.pdf Download (10MB) | Preview

Abstract or Description

This paper presents an application of the CASSM (Concept-based Analysis of Surface and Structural Misfits) framework to interactive machine learning for a bodily interaction domain. We developed software to enable end users to design full body interaction games involving interaction with a virtual character. The software used a machine learning algorithm to classify postures as based on examples provided by users. A longitudinal study showed that training the algorithm was straightforward, but that debugging errors was very challenging. A CASSM analysis showed that there were fundamental mismatches between the users concepts and the working of the learning system. This resulted in a new design in which aimed to better align both the learning algorithm and user interface with users' concepts. This work provides and example of how HCI methods can be applied to machine learning in order to improve its usability and provide new insights into its use.

Item Type:	Conference or Workshop Item (Paper)
Keywords:	Interactive Machine Learning; Movement Interfaces; Gesture Design; Conceptual Models;
Departments, Centres and Research Units:	Computing > Embodied AudioVisual Interaction Group (EAVI)
Dates:	Date Event March 2015 Published
Event Location:	Atlanta, United States
Item ID:	11381
Date Deposited:	27 Feb 2015 07:38
Last Modified:	29 Apr 2020 16:08
URI:	https://research.gold.ac.uk/id/eprint/11381

View statistics for this item...

Edit Record (login required)