[swsieber]

This is a nice idea. Once it gets large enough though, you're going to half to infer political leaning from what a person votes for, or else it'll be very easily abused.

I do think it's great though. I think I'll give it a whirl.

[mrbodoia]

Thank you! Yeah the potential for abuse of ideological self-identification is definitely what I'm most worried about.

I'm hoping that as long as there are enough truthful users, I can build a classifier based on their voting/commenting behavior and use it to detect "false-flagging." But for the time being I'll just have to manually moderate that kind of behavior.

[vectorpush]

Perhaps adding a way for users to tag a story as left or right leaning (or even more descriptive tags like anti-union, pro-life, anti-regulatory etc) might also provide some insight to your classifiers. How an individual classifies a story would only need to be visible to that user, but from a UX perspective it might encourage more honest input into the system that could be used to ground political viewpoints. You might find that a lot of partisans mark themselves as neutral, but most partisans won't be able to resist labeling a story in a manner that fits their partisan perspective.

[mrbodoia]

That's a great idea - so great that it's already on my feature list!

Post tags are something that I'm planning on implementing in the near future, though I'll need to think a little more about the best way to do them. I was planning to use them as a way of identifying topics only (e.g. abortion, immigration, taxes), but I like your idea of tagging particular stances as well.

[swsieber]

You might be able to alleviate it with NLP so you can divide articles into categories. I'm not entirely sure how you could use that to avoid the abuse, but it seems like it'd help be able to help.