To create a platform that could filter out biased and unreliable news sources.
What it does
"got bias?" filters news articles and ranks them according to a base algorithm that favors unbiased writers and reliable sources. On the "got bias?" website, a list of the top-ranked news sources is displayed. The algorithm also takes news date into account, so the most recent news is always near the top of the rankings.
How we built it
The sentiment analysis model was trained with data that was web-scraped using pythons scripts from news articles. The sentiment analysis model used Naive Bayes Classifier to analyze for bias. The ranked articles were then input into an Excel spreadsheet. The "got bias?" website was made with HTML/CSS and hosted using GitHub.
Challenges we ran into
Cleaning up the data was difficult, as the web-scraper script didn't provide the text of the article perfectly. We also had difficulty training the sentiment analysis model to find if the articles showed bias.
Accomplishments that we're proud of
We are proud of being able to successfully implement the sentiment analysis model.
What we learned
We learned about sentiment analysis modelling, as well as web-scraping with python scripts.
What's next for got bias?
We hope to deploy the bias checker remotely across all platforms so that anyone can use it.