Depends what you're trying to identify. If you're trying to identify "machine-generated", yes. If you're trying to identify "spam", probably not? Spam posted sarcastically is no more something I'd want in my comments section than spam posted by a bot.
True. However I'm sure an LLM would be able to filter that one out without problems. /s
In the case that it’s a human posting sarcastically, wouldn’t that be a false positive?
Depends what you're trying to identify. If you're trying to identify "machine-generated", yes. If you're trying to identify "spam", probably not? Spam posted sarcastically is no more something I'd want in my comments section than spam posted by a bot.
4 replies →