Multimodal Labeling and Characterization of Social Network Data for Detection/Prediction of Cyberbullying

Friday, April 21, 2017, 1:00 pm - 2:00 pm PSTiCal
11th floor large conference room
This event is open to the public.
AI Seminar - Interview talk
Homa Hosseinmardi

One of the most pressing problems in high schools is bullying. However, with today’s online and mobile technologies, bullying is moving beyond the schoolyards via cell phones, social networks, online text, videos, and images. As bad as fighting and bullying were before the internet age, the recording and posting of hurtful content online has magnified the harmful reach of bullying, enabling it 24/7. Cyberbullying is a growing problem and incidents of cyberbullying with extreme consequences such as suicide are routinely reported in popular press now. This talk provides insights into the problem of cyberbullying in social networks by investigating profanity usage, ground truth labeling of cyberbullying, and characterization of relationships between cyberbullying and a variety of factors, including linguistic content, social graph features, temporal commenting behavior, and multimedia modality. It also looks at the propagation of cyberbullying behavior in a social network, and prediction of victims of such behavior.

Bio: Homa Hosseinmardi holds PhD in Computer Science from the University of Colorado Boulder. She joined Danaher Corporation in 2015 as Data Scientist at Danaher Labs. She also contributes as a researcher at the CU CyberSafety Research Center. Hosseinmardi’s interests lie in the area of computational social science and data mining. She is particularly interested in the use of large-scale data sets and machine learning techniques to study problems with internet safety, misbehavior and cyberbullying. Her recent work has focused on studying triggers of cyberaggressive behaviors. Her past work also addressed various questions toward understanding cyberbullying in online social networks.

Webcast link:

« Return to Upcoming Events