Wright State University researchers, working out of the Ohio Center of Excellence in Knowledge-enabled Computing (Kno.e.sis), have developed software to analyze social media posts in an effort to identify and reduce cyberbullying.
The project, called Context-Aware Harassment Detection on Social Media, is funded by a $925,104 U.S. National Science Foundation grant.
In addition to analyzing the words used on social media, the researchers also analyzed the context of the posts, such as gender, age, location, and relationship. Social media posts can be further analyzed for identifying specific targets of the posts and expressions of sentiment, emotion, intent, culture, and attitude. The researchers found adding context leads to understanding features and properties that characterize harassment in a far more insightful way by considering name calling, appearance, and behavior with respect to such factors as power, familiarity, and truth, according to Amit Sheth, the project's principal investigator.
The researchers want to develop an educational program for students that will identify harassment. The program would include software that can emit a "harassment alert" and capture harassing messages.
If the techniques prove useful after testing, the software could be made available to the public.
From Wright State Newsroom
View Full Article
Abstracts Copyright © 2015 Information Inc., Bethesda, Maryland, USA