-
-
Logo
-
Icon
-
Popup
-
Workflow
-
HateBlocker on Twitter
-
HateBlocker on YouTube
In case video link doesn't work: https://drive.google.com/file/d/1hHHi9F8azNeBMf4PcFkScJ1aZgsslcgP/view?usp=sharing
Inspiration
The idea for HateBlocker came from the increasing negativity I found on the Internet. From Youtube comments to Tweets, it was easy to see how common negative and mean texts were all over the web. I hoped to build something that may make my and hopefully others' time on the Internet much more enjoyable. On top of that, I hoped to build something that would combat cyberbullying, which is something 15% of students between ages 12-18 who reported being bullied at school experience (Source: stopbullying.gov). By blocking out the "haters," HateBlocker can play a role in ensuring mental wellbeing while on the Internet.
Inspiration for the name: https://youtu.be/MtA5Xze0C4g (You'll see it in the logo)
What it does
HateBlocker pulls Tweets and Youtube comments and uses Google Cloud Platform's Natural Language API to run sentiment analysis on the text. HateBlocker then hides and blocks out potentially negative and hurtful text to provide a positive Internet experience.
How I built it
I used HTML to build the body of the Chrome extension, and I used Javascript to pull text from the web page and hide it if it had negative language. I also used Python with Flask to run the Natural Language API and return its assessment with an HTTP POST request.
Challenges I ran into
This was my first time ever building a chrome extension, so naturally, there were a lot of difficulties with getting used to content scripts and chrome.runtime. I also had to use quite a few asynchronous functions within synchronous ones in Javascript, so finding ways to work around those was a challenge.
Accomplishments that I'm proud of
I am proud of the fact that I was able to learn how to build a functioning Chrome extension with no prior experience and implement AI into a project. This project has been a major personal milestone as I have learned a lot of new skills and was able to deliver a functional prototype.
What I learned
It was really interesting to learn about how Chrome extensions interact and communicate with web pages. This was also my first time using AI in a project. I had read about Google's Natural Language API and wanted to see if I could use it.
What's next for HateBlocker
I hope to improve HateBlocker in the future so it can run smoothly and improve the accuracy of the AI to better detect negative texts. I also hope to make it compatible with more websites as right now it can only work with Twitter and Youtube.
Log in or sign up for Devpost to join the conversation.