Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I spent significant time on binary text classification, specifically with HN titles. You can actually get up to 65-70% post popularity accuracy just by looking at the post title.

I am currently creating a filter that filters HN news and similar sources using a similar classfier. It learns on the fly and the accuracy of guessing my 'taste' is about 75%-80%. Better accuracy for this is explainable by the fact that my interests are more focused and the classifier has easier time predicting posts I would be interested in.



Cool! I'm really curious about what you're up to since I'm doing something similar. Mine's up at https://www.onlyvetted.com/

Hit me up at kevmod at gmail, would love to hear more.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: