Tag: Twitter

System Detects & Translates Sarcasm on Social Media

Technion student develops system that interprets sarcasm on Twitter, and translates it into sarcasm-free language

Advertisements
Photo by Pixabay on Pexels.com

Researchers in the Technion-Israel Institute of Technology Faculty of Industrial Engineering and Management have developed a system for interpreting sarcastic statements in social media. The system, developed by graduate student Lotam Peled, under the guidance of Assistant Professor Roi Reichart, is called Sarcasm SIGN (sarcasm Sentimental Interpretation GeNerator).

“There are a lot of systems designed to identify sarcasm, but this is the first that is able to interpret sarcasm in written text,” said Peled. “We hope in the future, it will help people with autism and Asperger’s, who have difficulty interpreting sarcasm, irony and humor.”

Advertisements

Based on machine translation, the new system turns sarcastic sentences into honest (non-sarcastic) ones. It will, for example, turn a sarcastic sentence such as, “The new ‘Fast and Furious’ movie is awesome. #sarcasm” into the honest sentence, “The new Fast and Furious movie is terrible.”

Despite the vast development in this field, and the successes of sentiment analysis applications on “social media intelligence,” existing applications do not know how to interpret sarcasm, where the writer writes the opposite of what (s)he actually means.

In order to teach the system to produce accurate interpretations, the researchers compiled a database of 3,000 sarcastic tweets that were tagged with #sarcasm, where each tweet was interpreted into a non-sarcastic expression by five human experts. In addition, the system was trained to identify words with strong sarcastic sentiments – for example, the word “best” in the tweet, “best day ever” – and to replace them with strong words that reveal the true meaning of the text. The system was examined by a number of (human) judges, who gave its interpretations high scores of fluency and adequacy, agreeing that in most cases it produced a semantically and linguistically correct sentence.

Automatic identification and analysis of sentiment in text is a very complex challenge being explored by many researchers around the world because of its commercial potential and scientific importance. Sentiment identification could be used in social, commercial, and other applications to improve communication between people and computers, and between social media users.

Advertisements

The Technion-Israel Institute of Technology is a major source of the innovation and brainpower that drives the Israeli economy, and a key to Israel’s renown as the world’s “Start-Up Nation.” Its three Nobel Prize winners exemplify academic excellence. Technion people, ideas and inventions make immeasurable contributions to the world including life-saving medicine, sustainable energy, computer science, water conservation and nanotechnology. The Joan and Irwin Jacobs Technion-Cornell Institute is a vital component of Cornell Tech, and a model for graduate applied science education that is expected to transform New York City’s economy.

Advertisements

American Technion Society (ATS) donors provide critical support for the Technion—more than $2 billion since its inception in 1940. Based in New York City, the ATS and its network of supporters across the U.S. provide funds for scholarships, fellowships, faculty recruitment and chairs, research, buildings, laboratories, classrooms and dormitories, and more.

Advertisements

Increase Social Media Likability

Advertisements

Social media users who post a high percentage of selfies have lower perceived likability

Credit: iStock

A new Baylor University study published in the journal Psychology of Popular Media Culture looks at the value that outside observers place on social media cues (followers, likes, etc.) and measures the perceived likability of the people whose profiles were viewed.

WACO, Texas

Maybe you think your Facebook posts are hilarious. Or you might think that Instagram selfie of you at the beach is picture-perfect. And that clever Tweet? You nailed it! But what do other people – your “friends,” “followers” and anyone else who might stumble across your profile – think of you based on your social media presence? Do they really like you?

Advertisements

A new Baylor University study published in the journal Psychology of Popular Media Culture looks at the value that outside observers place on social media cues (followers, likes, number of selfies, etc.) and measures the perceived likability of the people whose profiles were viewed. The experimental study generated 873 decision responses from 72 experienced social media users who were asked to look at differing social media profiles and posts and then assess the likeability of the social media user.

“There are many studies of individuals’ self-perception through social media use. We are turning that around and looking at the audience’s perspective,” said the study’s lead author, Steven W. Bradley, Ph.D., associate professor of entrepreneurship in Baylor University’s Hankamer School of Business.

The study shows that “perceived likability” – a combination of perceived friendliness, relevance, empathy and realness – differed among men and women. Individual cue patterns confirmed several commonly held assumptions while combinations of social cues produced more intriguing findings, Bradley said. Researchers found:

  • Social media users who amass a larger number of friends and garner high numbers of likes on their posts have a higher perceived likability
  • Social media users who are considered physically attractive have higher perceived likability
  • Social media users who post a high percentage of selfies – photos featuring only themselves – have lower perceived likability
  • Males tend to value attractiveness more than females in assessing likability
  • Females tend to base perceived likability on numbers of followers, likes and percentage of selfies
Advertisements

Overall, the number of followers and likes are twice as important as attractiveness in predicting likeability, Bradley said. Alternatively, social media users with a higher percentage of selfies are considered 1.5 times less likeable by outside observers.   

Researchers found that users who were rated “low in attractiveness” gained more likability points, per se, if they had a large number of followers and likes. When social media users are viewed as “higher in attractiveness,” a change in the followers and likes from low to high increases perceived likeability by 20 percent. In contrast, for social media users who are perceived as lower in attractiveness, the difference in rated likeability between low and high followers and likes is 64 percent.

“In other words, numbers of followers and likes may be used by an observer to ‘make up’ for more obvious indicators like attractiveness when assessing likability,” the researchers wrote. “Most observers suggest that attractive people are likable due to associated attributes like social ease and confidence. A less attractive person with a high number of followers and likes suggest that other features – perhaps friendliness, relevance, empathy and realness – are the source of their social network, which also increase perceptions of likability.”

As for selfies? The researchers found that observers use their experience with cues regarding selfies to evaluate whether an authentic or manufactured self is presented.

“Too many selfies suggest the page owner is overly narcissistic and not a good friend candidate,” said study co-author James A. Roberts, Ph.D., The Ben H. Williams Professor of Marketing in Baylor’s Hankamer School of Business.

Likability diminished even when other social media status cues of followers or attractiveness were high.

“We hypothesized and found that a high percentage of selfies is a cue that may indicate less reciprocity and group benefit, focusing narcissistically on oneself relative to others,” the researchers wrote.

Advertisements

ABOUT THE STUDY

The study, “Experimental Evidence of Observed Social Media Status Cues on Perceived Likability,” is published in the journal Psychology of Popular Media Culture. Authors are Steven W. Bradley, Ph.D., associate professor of entrepreneurship, Baylor University Hankamer School of Business; James A. Roberts, Ph.D., The Ben H. Williams Professor of Marketing, Baylor University Hankamer School of Business; and Preston W. Bradley, student, Live Oak Classical School, Waco, Texas.

ABOUT BAYLOR UNIVERSITY Baylor University is a private Christian University and a nationally ranked research institution. The University provides a vibrant campus community for more than 17,000 students by blending interdisciplinary research with an international reputation for educational excellence and a faculty commitment to teaching and scholarship. Chartered in 1845 by the Republic of Texas through the efforts of Baptist pioneers, Baylor is the oldest continually operating University in Texas. Located in Waco, Baylor welcomes students from all 50 states and more than 80 countries to study a broad range of degrees among its 12 nationally recognized academic divisions.

ABOUT HANKAMER SCHOOL OF BUSINESS

Baylor University’s Hankamer School of Business provides a rigorous academic experience, consisting of classroom and hands-on learning, guided by Christian commitment and a global perspective. Recognized nationally for several programs, including Entrepreneurship and Accounting, the school offers 24 undergraduate and 13 graduate areas of study. Visit http://www.baylor.edu/businessand follow on Twitter at twitter.com/Baylor_Business.