Wednesday, March 31, 2021 11am to 12:15pm
About this Event
Examining untempered social media: Analysis of polarization and hate speech propagation
Abstract:
Online social media, periodically serves as a platform for cascading polarizing topics of conversation. The inherent community structure present in online social networks (homophily) and the advent of fringe outlets like Gab have created online "echo chambers" that amplify the effects of polarization, which fuels detrimental behavior. Recently, in October 2018, Gab made headlines when it was revealed that Robert Bowers, the individual behind the Pittsburgh Synagogue massacre, was an active member of this social media site and used it to express his anti-Semitic views and discuss conspiracy theories. This research presents a brief overview of methods to discover topics that are prevalent in such media and identify hate speech, particularly quantitatively uncover hateful users and present a tunable ensemble of deep learning models that leverages transfer learning to conduct automated hate speech classification on unlabeled datasets, like Gab.
Biography:
Siddharth Krishnan, an assistant professor of computer science at UNC-Charlotte, received his Ph.D. from Virginia Tech. His research is broadly interested in data mining and applied machine learning, particularly in solving big-data problems in large graphs and social media. Many of the research questions he answers deal with understanding efficiently, dynamical mechanisms (like propagation) on networks, to build explanatory and predictive models of data behavior and the groups of actors - people, societies, and organisms - that are captured by the data. His work has appeared in journals and conferences like AAAI, ACM WebSci, ACM WSDM, PLoS One, JMIR, IEEE ICMLA, etc.
0 people are interested in this event
User Activity
No recent activity