University of Denver
Design, Determination, and Evaluation of Gender-Based Bias Mitigation Techniques for Music Recommender Systems
Abstract
dc:description.abstractThe majority of smartphone users engage with a recommender system on a daily basis. Many rely on these recommendations to make their next purchase, download the next game, listen to the new music or find the next healthcare provider. Although there are plenty of evidence backed research that demonstrates presence of gender bias in Machine Learning (ML) models like recommender systems, the issue is viewed as a frivolous cause that doesn’t merit much action. However, gender bias poses to effect more than half of the population as by default ML systems are designed to cater to a cisgender man. This thesis takes a closer look into gender bias discovered in different ML/AI applications and provides a holistic view of bias mitigation measures proposed in literature. Then by means of user study on 20 participants this paper analyzes gender bias in music recommender systems and the efficiency of bias mitigation methods. Instead of detailing the bias mitigation methods in technical terms, this paper takes the approach of utilizing user reviews to understand the effectiveness of bias mitigation methods for gender biases. Finally, this work aims to propose solutions that can help create equitable ML/AI systems that profits all stakeholders.
Degree
thesis:*- Name thesis:degree_name
- M.S.
- Level thesis:degree_level
- Masters Thesis
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Shrestha, Sunny
- Contributors dc:contributor
-
- Sanchari Das
- Maria Calbi
- Daniel Pittman
- Kerstin Haring
Subjects
dc:subject × 11Rights
dc:rights- Statement dc:rights
-
- <p>Copyright is held by the author. User is responsible for all copyright compliance.</p>
- Sunny Shrestha
- Language dc:language
- en
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.du.edu/etd/2182