Researchers from the University of Central Florida working on DARPA’s Computational Simulation of Online Social Behavior (SocialSim) program are developing a solution to this challenge in the form of an AI-enabled “sarcasm detector.” The researchers have demonstrated an interpretable deep learning model that identifies words from input data – such as Tweets or online messages – that exhibit crucial cues for sarcasm, including sarcastic connotations or negative emotions. Using recurrent neural networks and attention mechanisms, the model tracks dependencies between the cue-words and then generates a classification score, indicating whether or not sarcasm is present.
See the article in the Defense Advanced Research Projects Agency news: https://www.darpa.mil/news-events/2021-05-06