By Stephen Beech via SWNS
A sarcasm detector that really works has been created by scientists.
Dutch researchers have developed an algorithm that they say is capable of identifying sarcasm by examining multiple aspects of audio recordings for increased accuracy.
Described as “the lowest form of wit, but the highest form of intelligence” by Oscar Wilde, sarcasm is notoriously difficult to convey through text and, even in person, it can be easily misinterpreted.
The Dutch team says the subtle changes in tone that convey sarcasm often confuse computer algorithms as well, limiting virtual assistants and content analysis tools.
They explained that traditional sarcasm detection algorithms often rely on a single parameter to produce their results, which is the main reason they often fall short.
Xiyuan Gao along with, Professor Shekhar Nayak and Professor Matt Coler, of the Speech Technology Lab at the University of Groningen, instead employed two complementary approaches – sentiment analysis using text and emotion recognition using audio – for a more complete picture.
PhD researcher Gao said: “We extracted acoustic parameters such as pitch, speaking rate, and energy from speech, then used Automatic Speech Recognition to transcribe the speech into text for sentiment analysis.
“Next, we assigned emoticons to each speech segment, reflecting its emotional content.
“By integrating these multimodal cues into a machine learning algorithm, our approach leverages the combined strengths of auditory and textual information along with emoticons for a comprehensive analysis.”
The Dutch team is optimistic about the performance of their algorithm, but they are already looking for ways to improve it further.
Gao said: “There are a range of expressions and gestures people use to highlight sarcastic elements in speech.
“These need to be better integrated into our project.
“In addition, we would like to include more languages and adopt developing sarcasm recognition techniques.”
The Dutch team says the same approach can be used for more than identifying a dry wit.
Gao said: “The development of sarcasm recognition technology can benefit other research domains using sentiment analysis and emotion recognition.
“Traditionally, sentiment analysis mainly focuses on text and is developed for applications such as online hate speech detection and customer opinion mining.
“Emotion recognition based on speech can be applied to AI-assisted health care.”
She added: “Sarcasm recognition technology that applies a multimodal approach is insightful to these research domains.”
The findings are due to be presented at a joint meeting of the Acoustical Society of America and the Canadian Acoustical Association in Ottawa, Canada.
