Computer science researchers at the University of Central Florida created a system that reliably senses sarcasm in social media content. The team successfully guided the computer model to look for clues that often signify sarcasm. They have thought the system to select cue words in sets too that were more likely to state sarcasm. They trained the system on how to do this by giving it massive data sets, which they then tested for reliability.
Source: https://www.sciencedaily.com/releases/2021/05/210507112040.htm
