ARLIS: UMD Researchers Measure Social Media Sharing with Emotions (ft. Susannah Paletz)

UMD ARLIS Staff - October 6, 2023

4,000+ Facebook posts were analyzed to determine the ability of different emotion models to predict post sharing.

Photo of a smart phone screen showing icons of social media apps

On average, people spend about two to three hours a day on social media platforms. It’s used for different things like sharing thoughts, understanding what is happening in the world and influencing others.

In a recently published article in Science Advances, University of Maryland (UMD) researchers have found that when individual emotions such as anger, contempt, love, admiration, cute/kama muta (an emotion described as ‘being moved’ or ‘heart-warming’) wonder, pride, sadness, and amusement are expressed in a post, there is a significant impact on whether it gets shared or not.

“There has always been concern about the spread of social media posts,” said Susannah Paletz, first author, associate professor at the UMD College of Information Studies and affiliate of the UMD Applied Research Laboratory for Intelligence and Security (ARLIS). “The purpose of this study was to understand the emotion theories that play into social media sharing.” Co-authors included Ewa M. Golonka, Nick Pandža, C. Anton Rytting, Devin Ellis (ARLIS), Michael Johns (Institute for Systems Research), Egle E. Murauskaite (ICONS Project) and Cody Buntain (College of Information Studies).

The team developed a research method to understand emotions in social media posts, also recently published at Behavior Research Methods. Both projects are part of the greater Emotions in Social Media UMD project, funded by the Minerva Research Initiative and the Office of Naval Research.

Independent judges analyzed more than 4,000 posts on Facebook in Poland and Lithuania for more than 20 emotions and then compared different models to predict how many times a post would be shared. The researchers compared different models that drew from three different theories of emotion.

Overall, the models that included specific emotions performed better in explaining sharing behavior on social media compared to models that grouped emotions differently. However, the model that included more than 20 different emotions was the most informative.

Controlling for number of followers, and other important covariates, posts with anger, contempt, love, admiration, cute/kama muta, wonder, pride, sadness, and amusement were associated with an increase in post sharing, whereas sexual attraction and happiness in posts were associated with a significant decrease in sharing.

Most of the research on emotions and social media sharing have used limited and outdated theories of emotion; the team was able to uncover findings that would not have been found if earlier theories were used.

Read more about the study, Emotional content and sharing on Facebook: A theory cage match, in Science Advances.

 

The original story by UMD Applied Research Laboratory for Intelligence and Security (ARLIS) staff was published by ARLIS on October 6, 2023.