Inspiration
We were inspired by the biased language we noticed in everyday conversations, the media, and even academic settings. We then researched the effect of bias and found that about 70% of employees feel that language bias creates a noninclusive environment. This inspired us to create a solution for reducing the amount of biased language that is used in society.
What it does
BiasBuster is a tool that helps identify biased language in text and suggests more inclusive alternatives. It scans the inputted written content for words or phrases that include stereotypes or reinforce harmful biases related to categories like gender, race, age, disability, appearance, and more. The user can input text and BiasBuster notices the biased terms and provides suggestions on how to make the terms more inclusive or neutral. BiasBuster also calculates a 'fairness score" to help users understand how inclusive their language is and encourages them to communicate respectfully.
How we built it
We utilized Python to build this successful program through VSCode.
Challenges we ran into
A challenge that we ran into was avoiding false positives, sometimes the program flagged words that weren’t biased depending on how they were used, which made us work harder on accuracy. Another one of the challenges we faced was organizing the categories, we had to carefully decide how to group different types of bias (like gender vs. stereotypes) without overlapping or missing things. We also struggled with making our code user-friendly because we wanted our code to be easy to understand and not too technical.
Accomplishments that we're proud of
We are proud of creating a program that will help others feel more inclusive and respected. We are also proud of the fact that we made a successful program and that we overcame the struggles that we came across.
What we learned
We have learned to implement the skills we have learned through online classes and classes in school. This hackathon is also a great experience to be creative and showcase our problem-solving skills.
What's next for BiasBuster
We plan to apply our program to a real application by turning it into a browser extension and a mobile app, making it more accessible for everyday use—especially for professionals and students. We’ll also invest in expanding our dataset to detect a wider range of biased terms and phrases more accurately. In the future, we hope to bring BiasBuster into classrooms by integrating it into lesson plans and school announcements, helping create a more inclusive and respectful environment for everyone.
Log in or sign up for Devpost to join the conversation.