Search for: All records

Inequitable software is a common problem. Bias may be caused by developers, or even software users. As a society, it is crucial that we understand and identify the causes and implications of software bias from both users and the software itself. To address the problems of inequitable software, it is essential that we inform and motivate the next generation of software developers regarding bias and its adverse impacts. However, research shows that there is a lack of easily adoptable ethics-focused educational material to support this effort.To address the problem of inequitable software, we created an easily adoptable, self-contained experiential activity that is designed to foster student interest in software ethics, with a specific emphasis on AI/ML bias. This activity involves participants selecting fictitious teammates based solely on their appearance. The participant then experiences bias either against themselves or a teammate by the activity’s fictitious AI. The created lab was then utilized in this study involving 173 real-world users (age 18-51+) to better understand user bias.The primary findings of our study include: I) Participants from minority ethnic groups have stronger feeling regarding being impacted by inequitable software/AI, II) Participants with higher interest in AI/ML have a higher belief for the priority of unbiased software, III) Users do not act in an equitable manner, as avatars with ‘dark’ skin color are less likely to be selected, and IV) Participants from different demographic groups exhibit similar behavior bias. The created experiential lab activity may be executed using only a browser and internet connection, and is publicly available on our project website: https://all.rit.edu. 

Research has demonstrated that much of the software being created today is not sufficiently inclusive, unbiased and equitable. This has been found to frequently result in real-world implications such as prejudice against women or people of color, and software that is inaccessible to people with disabilities. Preliminary research has found that empathyfocused experiential educational activities can be beneficial for not only creating empathy, but in advancing the participant’s interest and knowledge retention over traditional non empathy-building interventions. This work will provide a foundational background on the current research in the intersection of experiential learning and empathy-building interventions in computing education. We will also present several important questions that still must be explored, thus serving as the foundation for future work in this area.