Available at: https://digitalcommons.calpoly.edu/theses/2306
Date of Award
MS in Computer Science
College of Agriculture, Food, and Environmental Sciences
College of Engineering
Usability testing is an important part of product design that offers developers insight into a product’s ability to help users achieve their goals. Despite the usefulness of usability testing, human usability evaluations are costly and time-intensive processes. Developing methods to reduce the time and costs of usability evaluations is important for organizations to improve the usability of their products without expensive investments. One prospective solution to this is the application of facial emotion recognition to automate the collection of qualitative metrics normally identified by human usability evaluators.
In this paper, facial emotion recognition (FER) was applied to mock usability recordings to evaluate how well FER could parse moments of emotional significance. To determine the accuracy of FER in this context, a FER Python library created by Justin Shenk was compared with data tags produced by human reporters. This study found that the facial emotion recognizer could only match its emotion recognition output with less than 40% of the human-reported emotion timestamps and less than 78% of the emotion data tags were recognized at all. The current lack of consistency with the human reported emotions found in this thesis makes it difficult to recommend using FER for parsing moments of semantic significance over conventional human usability evaluators.