Inspiration
Advancements in technology are making it easier than ever for users to access information. Unfortunately, this includes disinformation - especially regarding the novel coronavirus. We wanted to create a program that allows users to do a sanity check on the information presented to them to make sure the information they are ingesting is reliable.
What it does
When the program is run, the user is presented with a form that allows them to input the content of an article, the title, and it's corresponding link. After filling out those forms and submitting, a machine learning algorithm predicts the content as legitimate or fake.
How I built it
Used pre-labeled data classifying COVID-19 new articles as either legitimate or fake to train machine learning model. Model was loaded into JavaFX form where user can input the link of a news article and its content. The form inputs are then concatenated and passed through the model, which classifies the input as legitimate or fake news.
Challenges I ran into
- Getting front end to work and Java to run Python script
- Data preprocessing for weblink formats
Accomplishments that I'm proud of
- Learning how to use a new machine learning method
- Learning to build a front end application (as a back end developer)
What I learned
- Frontend development with JavaFX
- Interaction across languages
- Implementing PassiveAggressiveClassifier
What's next
- Fully connect JavaFX file to Python script to automate process
- Turn program into a browser plugin to give predictions while user is browsing
Log in or sign up for Devpost to join the conversation.