The Speech Technology Laboratory of the University of Groningen has developed an AI-based sarcasm detector that can detect when such jokes are used.
People generally recognize sarcasm easily, but textual clues make this more difficult. Researchers trained a neural network to detect sarcasm based on text, audio and emotional content in video clips of TV shows such as Friends and The Big Bang Theory.
The database, known as Mustard, was created by scientists in the US and Singapore and is described with mocking labels.
After training in text and audio to assess the emotional content of words, the AI was able to detect sarcasm in untagged dialogue in TV series 75% of the time.
Further studies using synthetic data have improved accuracy, but these results have not yet been published.
Shekhar Nayak, one of the project researchers, stated that the technology can improve interaction with artificial intelligence assistants and help detect negative tone, harassment and hate speech.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
