Inspiration
Misinformation spreads much faster than true information does online, but normal people often do not put in the effort to check and verify such information. Often, it takes a long time to verify such information, so we were inspired to build this project.
What it does
Our browser extension, Article Checker lets the user highlight a claim that they want to check. Once the user highlights the sentence, the extension returns a verdict that shows whether the information is true, false, or inconclusive.
How we built it
We built this project using Plasmo, Typescript, and Serp Api.
Challenges we ran into
A challenge we ran into was connecting the backend to the browser extension. The NLP often returned INCONCLUSIVE, and thus we had to adjust confidence thresholds.
Accomplishments that we're proud of
We are proud of being able to build a full AI pipeline with both backend and frontend. Also, we are proud of the UI.
What we learned
We learned how to create a browser extension from scratch, connecting a backend to a frontend, and working collaboratively with Git.
What's next for Article Checker
We want to add inline highlighting on the page to show automatically as you read.
Built With
- javascript
- python
- serpapi
- typescript
Log in or sign up for Devpost to join the conversation.