Detecting and mitigating human bias in visual analytics
MetadataShow full item record
People are susceptible to a multitude of biases, including perceptual biases and illusions; cognitive biases like confirmation bias or anchoring bias; and social biases like racial or gender bias that are borne of cultural experiences and stereotypes. As humans are an integral part of data analysis and decision making in many domains, their biases can be injected into and even amplified by models and algorithms. This dissertation focuses on developing a better understanding of the role of human biases in visual data analysis. It is comprised of three high-level goals: 1. Define bias: We present four common perspectives on the term “bias” and describe how they are relevant in the context of visual data analysis. 2. Detect bias: We introduce a set of computational bias metrics that, applied to user interaction sequences in real-time, can be used to approximate bias in the user’s analysis process. 3. Mitigate bias: We describe a design space of ways in which visualizations might be modified to increase awareness of bias. We implement a system which integrates and visualizes the bias metrics and show how it can increase awareness of bias.
Showing items related by title, author, creator and subject.
Sonification and visualization of narrative: Getting computing students to think aurally and visually rather thn audio-visually Vickers, P. (Georgia Institute of TechnologyInternational Community for Auditory Display, 2004-07)In this paper we describe a final-year undergraduate honours course that requires multimedia computing students to create narrative auditory and visual displays. The aim was to use discontinuity as a catalyst for creativity ...
Choo, Jaegul; Lee, Changhyun; Park, Haesun (Georgia Institute of Technology, 2013)Abstract Visual analytics has been gaining increasing interest due to its fascinating characteristic that leverages both humans’ visual perception and the power of computing. Although various computational methods are ...
Preliminary guidelines on the sonification of visual artworks: Linking music, sonification & visual arts Nadri, Chihab; Anaya, Chairunisa; Yuan, Shan; Jeon, Myounghoon (Georgia Institute of TechnologyInternational Community on Auditory Display, 2019-06)Sonification and data processing algorithms have advanced over the years to reach practical applications in our everyday life. Similarly, image processing techniques have improved over time. While a number of image ...