Channel: Simply Explained

Category: Science & Technology

Tags: google sheetservereducationdataneuraltraininglearningartificial intelligencedeep learningtensorflowtext classifierspam filterjupyterpytorchclassifiereducatealgorithmnotebookmloverfittingpythonlearnhowtoaiunderstandmachine learningbraineasyscriptneural netspamcoreml

Description: 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. 🌍 Social Twitter: twitter.com/Savjee Facebook: facebook.com/Savjee Blog: savjee.be 💌 Newsletter: newsletter.savjee.be (Once a month) ❤️ Become a Simply Explained member: youtube.com/channel/UCnxrdFPXJMeHru_b4Q_vTPQ/join 👩‍💻 Source code: Available on GitHub: github.com/Savjee/yt-spam-classifier ❓❓ 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.