Understanding and responding to customer feedback on social media platforms is critical for brands, and it may just have gotten a little easier thanks to new research from computer science researchers at the University of Central Florida who developed a sarcasm detector.
Social media has emerged as a dominant mode of communication for both individuals and businesses seeking to market and sell their goods and services.
Understanding and responding to consumer feedback on Twitter, Facebook, and other social media platforms is critical for success, but it takes a lot of time. This is where sentiment analysis comes into play.
The term refers to the automated process of determining the emotion associated with the text, which can be positive, negative, or neutral.
While artificial intelligence is concerned with logical data analysis and response, sentiment analysis is concerned with correctly identifying emotional communication.
A UCF team developed a method for detecting sarcasm in social media texts.
The findings of the team were recently published in the journal Entropy.
The team effectively taught the computer model to find patterns that frequently indicate sarcasm and then combined that with teaching the programme to correctly identify cue words in sequences that were more likely to indicate sarcasm.
They trained the model to do this by feeding it large amounts of data and then testing its accuracy.
The team, which includes Ramya Akula, a computer science doctoral student, began working on this problem thanks to a DARPA grant that supports the organization’s Computational Simulation of Online Social Behavior programme.
Sarcasm And It’s Challenges
Sarcasm has been a huge impediment to improving sentiment analysis accuracy, particularly on social media, because sarcasm relies heavily on vocal tones, facial expressions, and gestures that can not be represented in text, according to Brian Kettler, a programme manager in DARPA’s Information Innovation Office (I2O).
CASL is an interdisciplinary research group dedicated to the study of complex phenomena such as the global economy, the global information environment, innovation ecosystems, sustainability, and the dynamics and evolution of social and cultural phenomena.
CASL researchers investigate these issues using a variety of approaches, including data science, network science, complexity science, cognitive science, machine learning, deep learning, social sciences, and team cognition.
Sarcasm can be easily identified in a face-to-face conversation by using facial expressions, gestures, and the speaker’s tone, according to Akula.
Complex systems, agent-based models, information and misinformation dynamics on social media, artificial intelligence, and machine learning are among his research interests.
He has over 75 peer-reviewed papers to his name and has received over USD 9.5 million in funding from various national agencies.
Leave a Reply