Technology careers and opportunities span nearly every aspect of the global economic spectrum. It also includes, now, the ability to read between the lines.
Social media, over the last decade, has become the second most utilized form of advertisement for companies and entrepreneurs everywhere. It’s second only to search engine advertising. This is a far cry from the power of TV advertising’s heyday. And it’s crucial more than ever to use it to engage with consumers, but it’s also difficult, laborious, and expensive.
Sentiment analysis is the phrase used to describe the automated process of determining the emotions behind textual content. This is separate from data analysis and logic interpretation. Think of it as computer-generated emotional awareness. On that note, a university group developed a method that can find sarcasm within social media posts.
You can read about this in much more detail in the Entropy journal that recently published their claims.
They surmised that the A.I. needed to seek out patterns associated with sarcasm and then developed algorithms to locate keywords that are typically used sarcastically. To verify their logistics, they had to dump a massive amount of text data into the software and test to see if it could effectively spot sarcasm.
Locating Sarcasm
“The presence of sarcasm in text is the main hindrance in the performance of sentiment analysis,” according to Assistant Professor of engineering Ivan Garibay ’00MS ’04PhD. “Sarcasm isn’t always easy to identify in conversation, so you can imagine it’s pretty challenging for a computer program to do it and do it well. We developed an interpretable deep learning model using multi-head self-attention and gated recurrent units. The multi-head self-attention module aids in identifying crucial sarcastic cue-words from the input, and the recurrent units learn long-range dependencies between these cue-words to better classify the input text.”
The group, including doctoral student Ramya Akula, was able to fund this project and start working because of a DARPA grant that provides for their Computational Simulation of Online Social Behavior program.
One significant debate is how machines can learn sarcasm when so many humans possess little to no ability to detect it online when engaging with others.
Is The Joke Lost On Us?
“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,” says 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 are readily available.”
This is the major problem that Garibay’s Complex Adaptive Systems Lab (CASL) is researching. CASL is a research team dedicated to the study of nebulous environments such as global economics, sustainability, cultural dynamics, and evolutionary trends. CASL studies these problems using data science, networking science, complexity science, A.I., and other tools.
“In face-to-face conversation, sarcasm can be identified effortlessly using facial expressions, gestures, and tone of the speaker,” Akula says. “Detecting sarcasm in textual communication is not a trivial task as none of these cues are readily available. Especially with the explosion of internet usage, sarcasm detection in online communications from social networking platforms is much more challenging.”
Credentials
Garibay is an assistant professor in Industrial Engineering and Management Systems. He has multiple degrees including a Ph.D. in computer science from UCF. Garibay is the director of UCF’s Artificial Intelligence and Big Data Initiative of CASL and of the master’s program in data analytics. His research areas include complex systems, agent-based models, information and misinformation dynamics on social media, artificial intelligence, and machine learning. He has more than 75 peer-reviewed papers and more than $9.5 million in funding from various national agencies.
Akula is a doctoral scholar and graduate research assistant at CASL. She has a master’s degree in computer science from the Technical University of Kaiserslautern in Germany and a bachelor’s degree in computer science engineering from Jawaharlal Nehru Technological University, India.
