With elections going on both in the United States and in Canada, we felt the urge and the need to poke fun at politics and the ridiculous statements made by politicians.
What it does
BSO'Meter takes direct text input or the URL of a website and gives the user an analyzed result that shows the percentage of BS in the text.
How we built it
We built the front-end in Xcode, using Swift 2.0; back-end programming is done in python and incorporating Algorithmia's machine learning and text analysis APIs; our server was built on Tornado.
Challenges we ran into
We were planning to use IBM Watson's APIs as well but we encountered login issues. Troubleshooting was taking too long so we decided to do without it. We also ran into challenges when trying to use Tesseract for OCR in Swift.
Accomplishments that we are proud of
What we learned
What's next for BSOmeter
Better algorithms, use ML and NLP to improve analysis accuracy, OCR, and processing real-time voice input.