A team of university researchers in the Netherlands says they've developed an artificial intelligence (AI) platform that can recognize sarcasm, according to a new report.
The Guardian reported on Thursday that the research was presented at a meeting of the Acoustical Society of America and the Canadian Acoustical Association in Ottawa, Canada, on Thursday. At the event, Ph.D. student Xiyuan Gao said the research team used video clips and other text and audio content from American sitcoms like "Friends" and "The Big Bang Theory" to train a neural network.
The work leveraged a database called the Multimodal Sarcasm Detection Dataset (MUStARD), which another research team from the U.S. and Singapore had annotated with labels about whether sarcasm was present in a given piece of content as part of a push to build their own sarcasm detector.
After training their AI model on the data, the researchers said they're able to detect sarcasm in exchanges that were unlabeled by the researchers almost 75% of the time. They added that subsequent work at the lab using synthetic data has improved that accuracy level even further, though those research findings haven't yet been published, The Guardian wrote.
Among the content from TV shows in the database used to train the AI model about sarcasm were a scene from "The Big Bang Theory" in which Sheldon observes his friend and roommate Leonard unsuccessfully attempting to escape from a locked room, as well as a scene from "Friends" that shows Chandler, Joey, Ross and Rachel unenthusiastically assembling furniture.
"We are able to recognize sarcasm in a reliable way, and we're eager to grow that," Matt Coler, a researcher at the University of Groningen's speech technology lab, told the outlet. "We want to see how far we can push it."
Shekhar Nayak, another member of the research project, said the team's methods and findings could help AI assistants interact more easily with human speakers by detecting negativity or hostility in the speaker's voice.
Gao noted that incorporating visual cues into the AI tool's training data could make it even more capable of detecting sarcasm conveyed through facial expressions like raised eyebrows or smirks.
The interest in AI-powered sarcasm detection shown by the University of Groningen research team and the researchers who compiled the sarcasm-annotated MUStARD content database follows a similar line of research done by the U.S. Department of Defense in recent years.
The Pentagon's Defense Advanced Research Projects Agency (DARPA) and researchers from the University of Central Florida used DARPA's SocialSim program to develop an AI model capable of classifying whether a piece of text such as a social media post or text message contains sarcasm.
"The team demonstrated the effectiveness of their approach by achieving state-of-the-art results on multiple datasets from social networking platforms and online media," DARPA wrote in 2021. "The model was able to successfully predict sarcasm, achieving a nearly perfect sarcasm detection score on a major Twitter benchmark dataset as well as state-of-the-art results on four other significant datasets."
"Accurately detecting sarcasm in text is only a small part of developing these simulation capabilities due to the extremely complex and varied linguistic techniques used in human communication. However, knowing when sarcasm is being used is valuable for teaching models what human communication looks like, and subsequently simulating the future course of online content," it added.
