Hacker News Reader

They seem to jump on any chance to promote their technology. Very aggressive and annoying marketing. If the articles had any meat to them, I'd nod and move on, but this seems just a cheap plug.

My BS-meter went way up, when I scrolled down and saw the charts that conveniently "verified" the sentiment on Hacker News. I hope they don't think I typed this message, because I am depressed and lack compassion.

View on HN

More meta: at this point I have no reason to see their measurements as anything other than hocus-pocus. What I've read of their description of it so far has amounted to classifying words -- context-free -- as "anxious" words, "depressed" words, and so on, and then simply counting their occurrence in text.

I would be hugely surprised if that actually gave reliable results! Human languages are hugely nuanced and context is a key part of interpreting mood in text, and even humans fail often at that. People often express surprise, for example, at pg's personality in person or in televised events, because his comments often seem (as one person put it) "Vulcan".

I'm starting to try to think of ways to thoroughly debunk their method, mostly because I'm curious if it would actually stand up.

Reply on news.ycombinator.com