公开(公告)号：US20220182351A1

公开(公告)日：2022-06-09

申请号：US17546648

申请日：2021-12-09

Applicant: Arizona Board of Regents on Behalf of Arizona State University

Inventor： Lu Cheng ,  Kai Shu ,  Siqi Wu ,  Yasin Silva ,  Deborah Hall ,  Huan Liu

IPC: H04L51/52 ,  H04L51/00 ,  H04L67/50 ,  G06F40/30 ,  G06N3/08

Abstract: A computer-implemented framework and/or system for cyberbullying detection is disclosed. The system includes two main components: (1) A representation learning network that encodes the social media session by exploiting multi-modal features, e.g., text, network, and time; and (2) a multi-task learning network that simultaneously fits the comment inter-arrival times and estimates the bullying likelihood based on a Gaussian Mixture Model. The system jointly optimizes the parameters of both components to overcome the shortcomings of decoupled training. The system includes an unsupervised cyberbullying detection model that not only experimentally outperforms the state-of-the-art unsupervised models, but also achieves competitive performance compared to supervised models.

公开(公告)号：US11916866B2

公开(公告)日：2024-02-27

申请号：US17546648

申请日：2021-12-09

Applicant: Arizona Board of Regents on Behalf of Arizona State University

Inventor： Lu Cheng ,  Kai Shu ,  Siqi Wu ,  Yasin Silva ,  Deborah Hall ,  Huan Liu

IPC: H04L51/52 ,  G06N3/088 ,  G06F40/30 ,  H04L51/212 ,  H04L67/50

CPC classification number: H04L51/52 ,  G06F40/30 ,  G06N3/088 ,  H04L51/212 ,  H04L67/535

Abstract: A computer-implemented framework and/or system for cyberbullying detection is disclosed. The system includes two main components: (1) A representation learning network that encodes the social media session by exploiting multi-modal features, e.g., text, network, and time; and (2) a multi-task learning network that simultaneously fits the comment inter-arrival times and estimates the bullying likelihood based on a Gaussian Mixture Model. The system jointly optimizes the parameters of both components to overcome the shortcomings of decoupled training. The system includes an unsupervised cyberbullying detection model that not only experimentally outperforms the state-of-the-art unsupervised models, but also achieves competitive performance compared to supervised models.