Fighting Spam on YouTube with TensorFlow & Python

Publié le: 25 juin 2021
sur la chaîne: Simply Explained
25,331
1k

I'm sick of crypto-related spam comments on YouTube, so I trained a machine learning model to delete them! A script runs periodically and uses the text classifier to filter the latest comments on my videos.

The filter is surprisingly effective, even though the training dataset is relatively small. I'll keep expanding the dataset and retrain the classifier so it becomes more accurate overtime.

💌 Sign up for Simply Explained Newsletter:
https://newsletter.simplyexplained.com
Monthly newsletter with cool stuff I found on the internet (related to science, technology, biology, and other nerdy things)! No spam. Ever. Promise!


🌍 Social
Twitter:   / savjee  
Facebook:   / savjee  
Blog: https://savjee.be



❤️ Become a Simply Explained member:    / @simplyexplained  

👩‍💻 Source code:
Available on GitHub:
https://github.com/Savjee/yt-spam-cla...

❓❓ Frequently asked question:
❓ Why do I still see spam comments on your channel?
First, not all comments are caught by the AI and still require manual intervention. Secondly, the script runs on a fixed interval. Give it some time to run. And thirdly, it only filters recent comments. I will let the classifier clean up the old comments as well.


Sur cette page du site, vous pouvez voir la vidéo en ligne Fighting Spam on YouTube with TensorFlow & Python durée heure minute seconde en bonne qualité , qui a été Téléchargé par l'utilisateur Simply Explained 25 juin 2021, Partagez le lien avec vos amis et connaissances, sur youtube cette vidéo a déjà été regardée 25,331 fois et il a aimé 1 mille téléspectateurs. Bon visionnage!