Hacker News Reader

Comment by alx__ | Hacker News Reader

Language is hard! Even I, a seasoned native internet dork, have trouble knowing if someone's comment is sarcasm, irony, or something in between. Also, new phrases emerge all the time that turn a phrase on its head, and it has a different emotion.

How many feelings can you evoke with a simple, FUCK!

View on HN

And this is probably going to get even worse the more automatic classification is used to promote or silence content.

A pretty interesting result of this is what I'd call "TikTok speak", where words are replaced, either by similar sounding ones ("porn" => "corn", often times just the corn emoji) or by neologisms ("to kill" => "to unalive"), in the hope of getting around the filters.

This turns natural language on the internet into even more of a moving target than it already used to be.

The core of the problem is unsolvable, since any automated system can be defeated by a sufficiently motivated human.

The most interesting thing is imo that people often say one thing, but put a similar-sounding word or a homophone in the subtitles, and the filter seems to trust the user-supplied subtitles.

I hope nobody trains speach-to-text systems on a tiktok dataset.

I feel like this is basically a subset of the translation problem, which you probably need actual artificial general intelligence for (because you need to be able to model another human mind to a certain degree). Here's a neat video covering the topic [1].

1: https://www.youtube.com/watch?v=GAgp7nXdkLU

Further compounded by the fact that often if I say something and get asked, "was that sarcasm, irony, or something in between?" the best I can probably do is "Eh, more or less".

The last person I'd expect that would be good at detecting sarcasm, irony or any intonation change is an internet dork.

Reply on news.ycombinator.com