My Data Labeler
My Data Labeler is an open-source text classification tool.
I believe there aren't enough open source text classification tools out there, so I built my own! It is still a work in progress and will hopefully be completed by December 2020. It is built on Angular as the front-end, MongoDB as the database, and MongoDB Stitch for user management and a server-less back-end. Also, I manage the code using git and is stored on GitHub. I am hoping to have a website for this project in the near future.
This project stems from one of my passions: language. Ever since I can remember, I have been fascinated with the world's languages. In high school I took all 5 available Spanish courses, earned my Minor in Spanish at college, and studied in Burgos, Spain for 2 months in the summer of my sophomore year. Language translators like Google Translate (although relatively inaccurate) intruiged me. That drove me to learn more about natural language processing and deep learning. In my senior year of college I studied this and submitted a paper to the West Virginia Academy of Science and got to present my studies at their annual conference.