-
公开(公告)号：US20210089579A1
公开(公告)日：2021-03-25
申请号：US17018877
申请日：2020-09-11
Inventor： Kai Shu , Deepak Mahudeswaran , Huan Liu
IPC: G06F16/906 , G06F16/9035 , G06F16/903 , G06F16/9032 , H04L12/58 , G06F16/951
Abstract: Detecting fake news involves analyzing a distribution of publishers who publish many news articles, analyzing a distribution of various topics relating to the published news articles, analyzing a social media context relating to the published news articles, and detecting fake news articles among the news articles based on the analysis of the distribution of publishers, the analysis of the distribution of the various topics, and the analysis of the social media context. Detecting fake news alternatively involves receiving online news articles including both fake online news articles and real online news articles, creating a hierarchical macro-level propagation network of the fake online news and real online news articles, the hierarchical macro-level propagation network comprising news nodes, social media post nodes, and social media repost nodes, creating a hierarchical micro-level propagation network of the fake online news and real online news articles, the hierarchical micro-level propagation network comprising reply nodes, analyzing structural and temporal features of the hierarchical macro-level propagation network, analyzing structural, temporal, and linguistic features of the hierarchical micro-level propagation network, and identifying fake news among the online news articles based on the analysis of the structural and temporal features of the hierarchical macro-level propagation network and the analysis of the structural, temporal, and linguistic features of the hierarchical micro-level propagation network.
-
公开(公告)号：US20220182351A1
公开(公告)日：2022-06-09
申请号：US17546648
申请日：2021-12-09
Inventor： Lu Cheng , Kai Shu , Siqi Wu , Yasin Silva , Deborah Hall , Huan Liu
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：US20170212943A1
公开(公告)日：2017-07-27
申请号：US15412955
申请日：2017-01-23
Inventor： Jundong Li , Xia Hu , Jiliang Tang , Huan Liu
IPC: G06F17/30
CPC classification number: G06F16/248 , G06F16/22 , G06F16/24568 , G06F16/24578 , G06F16/9024 , G06F16/9535
Abstract: Systems and methods for exploiting link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework are disclosed.
-
4.发明申请SYSTEMS AND METHODS FOR PREDICTING PERSONAL ATTRIBUTES BASED ON PUBLIC INTERACTION DATA 审中-公开基于公共交互数据预测个人特征的系统和方法公开(公告)号：US20170004403A1
公开(公告)日：2017-01-05
申请号：US15161855
申请日：2016-05-23
Inventor： Pritam Gundecha , Jiliang Tang , Huan Liu
CPC classification number: G06N20/00
Abstract: Embodiments of a system for determining personal attributes based on public interaction data are illustrated. In one embodiment, the system employs a process for predicting personal attributes based on public interaction data by constructing matrices based on user interactions drawn from public posts on a social media website. The process may further learn a compact representation for a plurality of users based on public posts using the matrices, extract the compact representation of one or more users that have been labeled, and apply a classifier to learn about a particular personal attribute. Through this, a prediction of personal attributes of users that have not been labeled may be obtained.
Abstract translation: 示出了基于公共交互数据来确定个人属性的系统的实施例。 在一个实施例中，该系统采用基于公共交互数据来预测个人属性的过程，该过程是通过基于社交媒体网站上的公开帖子中提取的用户交互构建矩阵来构建矩阵。 该过程可以基于使用矩阵的公共帖子进一步学习多个用户的紧凑表示，提取已标记的一个或多个用户的紧凑表示，并应用分类器来了解特定个人属性。 通过这样，可以获得未被标记的用户的个人属性的预测。
-
5.发明申请公开(公告)号：US20230117980A1
公开(公告)日：2023-04-20
申请号：US17938589
申请日：2022-10-06
Inventor： Kaize Ding , Jianling Wang , Huan Liu
Abstract: A system employs Graph Prototypical Networks (GPN) for few-shot node classification on attributed networks, and a meta-learning framework trains the system by constructing a pool of semi-supervised node classification tasks to mimic the real test environment. The system is able to perform meta-learning on an attributed network and derive a highly generalizable model for handling the target classification task. The meta-learning framework addresses extraction of meta-knowledge from an attributed network for few-shot node classification, and identification of the informativeness of each labeled instance for building a robust and effective model.
-
Patent Agency Ranking
公开(公告)号：US11418476B2
公开(公告)日：2022-08-16
申请号：US16435064
申请日：2019-06-07
Abstract: Messages are transmitted in a social media network. Embeddings of social media network users in the social media network are inferred. Propagation pathways over which the plurality of messages are transmitted through the social media network are classified. Action is taken on one or more of the messages that are transmitted through the social media network, based on the classification of the propagation pathways over which the messages are transmitted through the social media network and the inferred embeddings of the social media network users.
-
公开(公告)号：US10942939B2
公开(公告)日：2021-03-09
申请号：US15412955
申请日：2017-01-23
Inventor： Jundong Li , Xia Hu , Jiliang Tang , Huan Liu
IPC: G06F17/00 , G06F7/00 , G06F16/248 , G06F16/22 , G06F16/901 , G06F16/2455 , G06F16/2457 , G06F16/9535
Abstract: Systems and methods for exploiting link information in streaming feature selection, resulting in a novel unsupervised streaming feature selection framework are disclosed.
-
公开(公告)号：US20200065292A1
公开(公告)日：2020-02-27
申请号：US16550937
申请日：2019-08-26
Inventor： Jundong Li , Harsh Dani , Xia Hu , Huan Liu
IPC: G06F15/173 , H04L29/06 , H04L12/26
Abstract: A processor is configured with a learning framework to characterize the residuals of attribute information and its coherence with network information for improved anomaly detection.
-
公开(公告)号：US11916866B2
公开(公告)日：2024-02-27
申请号：US17546648
申请日：2021-12-09
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.
-
公开(公告)号：US10664764B2
公开(公告)日：2020-05-26
申请号：US15161855
申请日：2016-05-23
Inventor： Pritam Gundecha , Jiliang Tang , Huan Liu
IPC: G06N20/00
Abstract: Embodiments of a system for determining personal attributes based on public interaction data are illustrated. In one embodiment, the system employs a process for predicting personal attributes based on public interaction data by constructing matrices based on user interactions drawn from public posts on a social media website. The process may further learn a compact representation for a plurality of users based on public posts using the matrices, extract the compact representation of one or more users that have been labeled, and apply a classifier to learn about a particular personal attribute. Through this, a prediction of personal attributes of users that have not been labeled may be obtained.
-
-
-
-
-
-
-
-
-
Search Results
12
records
(took 0.029 seconds)
