A computer model aims to help better predict people's emotional reactions to Facebook posts!
Researchers at Penn State's College of Information Sciences and Technology have developed a computer model that could one day be used to better predict people's emotional reactions to Facebook posts. It could help users and companies understand the increasingly complicated ways people express their emotions on social media.
Create reliable results
“We want to understand the user reactions behind these Facebook reaction clicks. By modeling the problem as a ranking problem, an algorithm can predict the correct order among six emoticons in relation to the votes given a Facebook post,” explains researcher Jason Zhang. According to the researcher, current models do this too unreliably. Simply counting clicks would not adequately confirm that some emoticons are less likely to be clicked.
The researchers therefore want to develop a better model that predicts reactions as accurately as it did before 2016, when there was only one “like”. The researchers are now working with six options. The researchers, who will present their results at the AAAI Conference on Artificial Intelligence in New Orleans, used an AI technique called “supervised machine learning.” In the study, they trained the model on four Facebook post datasets, including public posts from regular users, the New York Times, the Wall Street Journal, and the Washington Post. They showed that their model outperformed existing solutions.
Understanding six emotions
For example, according to the scientists, users most often click the “Like” button because it signals a positive interaction. This is also the default emoticon on Facebook. “When we post something on Facebook, our friends tend to click on the positive reactions. Usually 'Heart,' 'Haha,' or just 'Like,' but they will rarely choose 'Angry,'" Zhang said. “This is causing a serious imbalance problem.”
For social media managers and advertisers who spend billions each year buying Facebook ads, this imbalance can impact their analysis of how their content actually performs on Facebook. For this reason, the researchers want to create a working computer model that can correctly calculate six emoticons in a Facebook post.
Notes:
1) This content reflects the current state of affairs at the time of publication. The reproduction of individual images, screenshots, embeds or video sequences serves to discuss the topic. 2) Individual contributions were created through the use of machine assistance and were carefully checked by the Mimikama editorial team before publication. ( Reason )