UC Berkeley Master of Design - Cultivating Gender Equity In the Workplace

In collaboration with a team of designers in a UC Berkeley Master of Design course, I created an iOT office plant that auto tracks microagressions as a way to promote gender equality in the workplace. I programmed automatic timestamps and microagression trackers on Google Sheets based on speech input by using Sheets and Drive APIs.
Role
Product Designer/Engineer
Timeline
2 months (Nov - Dec ‘21)
Core Responsibilities
Programming, User Research

Problem

Women experience discrimination in the workplace — resulting in pay inequities and unsafe work environments

It costs 6 to 9 months' salary on average to replace an employee. Based on user research with 5 interviewees, we identified thatDiscrimination is underreported — causing it to persist because of:

- Lack of awareness of microagressions
- Lack of tangible evidence of discrimination
- Lack of accountability to uphold fair behavior

Goals

Increase reporting of gender discrimination to raise awareness of microagressions

Our team created the concept of an iOT plant, designed and fabricated by Benal Johnson. Our goals were to:Increase awareness of microagressions by automatically tracking themCreate tangible evidence of discrimination by documenting when the microagression was made and where (room plant is in)Increase accountability to uphold fair behavior by creating weekly reports to demonstrate progress that indicates what actions should be taken

Risks: Privacy concerns

Programming

Creating automatic timestamps upon detecting microagressions by leveraging Google APIs

Using Google Sheets and Google Drive APIs, I programmed our algorithm to automatically record timestamps in addition to whether or not our plant wilted (microagression) or flourished (positive statements). This information could then be used to in accountability reports that could track quantitative progress over time. I collaborated with Hannah Bartolomea, who worked on the speech/NLP portion and sentiment analysis. I helped connect both parts of our code to function together.

Solution

An automatic, aesthetic, and integral way to track gender inequality

In the digital screen, represented by Raspberry Pi, it records how many “wilts” or “flourishes” have been automatically detected based on Sentiment Analysis (by Hannah Bartolomea). This information is automatically sent to Google Sheets and displays what happened (my contribution).When the plant flourishes, it turns green. When it wilts, it turns red.
Neopixel ring shines red light if negative speech is detected and a wilt effect is created
Neopixel ring shines green light if positive speech is detected and a flourish effect is created

Conclusion

Exploring and programming AI for the first time

This was uncharted territory for me, but I learned to tackle technical challenges in ways I never did before. I got to learn the mechanics of how AI works through NLP and build my own interactive product outside the usual digital realm, what I've been so used to for the past years.