[Seminar] Dealing with violence and hateful behavior in social networks through language and vision
Wednesday, June 7, 2023
11:00 am - 12:00 pm
Speaker
Hugo Jair Escalante
Senior
Research
Scientist
at
INAOE,
Mexico
Location
PGH
563
Abstract
Violence has obvious negative effects on those who witness or experience it, including a higher incidence of depression, anxiety, post-traumatic stress disorder, among others. In addition, violence events have a high impact for governments, as they are in charge of guaranteeing security to their population. The flourishing of social networks has broken the barriers for violence, as attacks can reach a massive amount of users. On the other hand, social networks comprise a valuable resource to track potential offenders and to monitor violent activity. In this talk I will present work carried out in the language technologies lab at INAOE on the detection and monitoring of hate speech and violent incidents in social networks. On the one hand, new models based on hybrid attention mechanisms are used to detect hate speech from textual and multimodal sources. On the other hand, a shared-task on the detection of mentions of violent incidents from multimodal information is described. Results of reference and state of the art models in this task are presented. Promising research directions on dealing with violence and hateful behavior in social networks will be discussed.
About the Speaker
Hugo Jair Escalante is senior researcher scientist INAOE, Mexico, member of the board of directors of ChaLearn USA, Chair of the IAPR Technical Committee 12, regular member of the Mexican Academy of Sciences (AMC) and Mexican System of Researchers Level II (SNI). Associate Editor of the IEEE Transactions on Affective Computing. Editor of the Springer Series on Challenges in Machine Learning 2017-2023. He has been involved in the organization of several challenges in machine learning and computer vision collocated with top venues, see . He has served as competition chair of FG2024, NeurIPS2020, FG2020 and ICPR2020, NeurIPS2019, PAKDD 2019-2018, IJCNN2019. Hugo has served as area chair for NIPS/NeurIPS, ACL, ICML and has been a member of the program committee of venues like CVPR, ICPR, ICCV, ECCV, ICML, NIPS, IJCNN. His research interests are on challenge organization, machine learning, and its applications on language and vision
