Inspiration
We were inspired by the amount of harassment/hostility towards women that goes on in Discord. We wanted to create a bot that protects women on the platform.
What it does
Basically, it's a moderation bot. So, when it detects that someone says something sexist, it gives a bunch of reactions and calls them out in the chat. Furthermore, it basically gives someone a strike. After 3 strikes, it kicks someone from the server.
How we built it
We built this bot with the help of a tutorial from Google Cloud. We cloned their 'making_with_ml' repo and modified it to fit our needs. This bot uses machine learning to detect the messages. The Perspective API analyzes messages and is able to forecast and confront emerging threats, which was beneficial for our scenario. Then, we set up a Discord bot, added it to a server, and tested it out. We did our coding on repl.it.
Challenges we ran into
Unfortunately, our bot did not behave as we expected it to, and we did not have enough time to fix it. However, it was a great learning experience.
Accomplishments that we're proud of
We're proud of going for a machine learning project even though we were all pretty much novices in machine learning.
What we learned
For one of our members(V), it was their first time working with Python! One of our other members, Yaritza, worked with ML for the first time. For me(Lailah), I became more comfortable with Google Cloud and I learned about how ML can be used to moderate servers
What's next for Femi bot
We hope to actually get it working so that it can be used to help women!
Built With
- google-cloud
- javascript
- python
- repl.it


Log in or sign up for Devpost to join the conversation.