Researchers from the University of Central Florida have devised an Artificial Intelligence mechanism that can actually detect sarcasm in social media posts. This is considered to become extremely beneficial to those companies that are looking to read their customers in a better manner and provide customised services to suit their target audience.
This AI is all set to revolutionize the field of customer relations, since most brands’ primary problem is understanding the customer and providing better services by listening to feedback.
“Sarcasm has been a major hurdle to increasing the accuracy of sentiment analysis, especially on social media, since sarcasm relies heavily on vocal tones, facial expressions and gestures that cannot be represented in text,” said Brian Kettler, a program manager in DARPA’s Information Innovation Office (I2O). “Recognizing sarcasm in textual online communication is no easy task as none of these cues is readily available,” he added
This AI has been built using a new technology called sentiment analysis. This is an automated mechanism that refers to sensing systems that can detect emotions like happiness, anger, and such and detecting whether it is positive, negative, or neutral-toned. This was researched by a team from UCF who went on to publish it in a journal called Entropy. The team taught the program to find patterns of sarcasm in text by using several kinds of words and sequences that might indicate sarcasm. They fed large sets of data to this program and iterated to nail the accuracy.
Click here to subscribe to The Commune on Telegram and get the best stories of the day delivered to you personally.