Abstract
My technical project titled "Analysis of Supreme Court Justice's Voting Behavior:
Correlation One's Data Science 4 All/Empowerment Project" and my STS research paper titled "Analysis of Amazon's Rekognition Software using the Actor-Network Theory" share the theme of the lack of diversity in data science and artificial intelligence. Correlation One's Data Science 4 All/Empowerment program (DS4A), the program through which I did my technical project, was created to address the lack of data science professionals from under-represented communities. Meanwhile, Amazon's Rekognition software was criticized for its inability to identify women and people with dark skin. Both papers critique the industry and its lack of diversity by showing the negative effects of the issue and how some companies are making initiatives to address it.
Members of the DS4A program engaged in a 13-week training course in which we learned industry-level data science techniques and skills. We also received mentorship from data science professionals and discussed ways in which to tackle the field's lack of diversity. Through the program, I created an insightful interactive dashboard that analyzes Supreme Court Justice's Voting Behavior. We did so by acquiring a federal data set with information about the Supreme court and its justices from its creation in 1789 to 2019. We cleaned and analyzed the data set using the techniques we learned from the program lecturers and presented our insights on a publicly accessible interactive dashboard. We found that contrary to survey data, the justices tend to vote with the majority, and they typically reverse the discussion of the lower courts.
Additionally, in the STS Research Project, I analyzed Amazon's Rekognition Software and deemed it unethical after evaluating the software through the Actor-Network-Theory. It was revealed that while the facial recognition software was made to be used by a wide audience, it was not able to accurately identify women and people with darker skin tones. The rogue actors in this network were the non-diverse data set, which led to a software trained to be most accurate for white men only, and the non-diverse team of software developers who, as network builders, were not able to advocate for the underrepresented users that will interact with their products, they excluded a section of their customer base.
By working on both projects, I identified the effect of the lack of diversity and the steps that were taken to address the issue. At Amazon, the lack of diversity contributed to the failure of the software and they were unable to serve a portion of their customer base. For the latter, Correlation One created the DS4A program to address situations in which professionals were not diverse enough to advocate for minority communities. These projects prompted me to reflect on how companies choose to respond to issues in tech and how that affects the companies' image and customer base, as well as the industry itself. Without Correlation One's program, I would not have known that there are people consistently advocating for inclusion and creating a tangible program to address it, and without Amazon's software, I would not be aware of how pioneers in the industry fail to recognize and address pressing issues. As a professional in the field, I hope that I will be able to advocate for all actors in society and ensure that the products I create and innovate will serve as many people as possible with no group being excluded.
