Hacker News Reader

I don't understand what's to stop the system accidentally generating sponsored ads following negative interaction with a brand: you'd get John Smith says - Starbuck's sucks! - sponsored story!

View on HN

What's nifty about the mechanism is that it doesn't, at least for now and according to the article, require the ever so difficult sentiment analysis. You have to explicitly "like" something or check in. Some users will have fun abusing this, but not so much more than some researchers abuse machine learning/nlp who complicate their living by putting too many constraints on a machine intelligence task. (Don't get me wrong, I love machine learning/nlp; it just doesn't have to be more complicated than it already is.)

"You have to explicitly "like" something or check in."

This only works if the "like" actions are filtered to company-approved material only. Otherwise you can "like" a post trashing the company.

Yep. I'm sure FB will be smart about it.

I wonder if they filter that out using a mood interpreter, like the ones that have been applied to twitter messages?

Reply on news.ycombinator.com