1,567 Hits in 7.0 sec

Rumor Detection with Self-supervised Learning on Texts and Social Graph [article]

Yuan Gao, Xiang Wang, Xiangnan He, Huamin Feng, Yongdong Zhang
2022 arXiv   pre-print
However, existing works on rumor detection fall short in modeling heterogeneous information, either using one single information source only (e.g. social network, or post content) or ignoring the relations  ...  Specifically, given two heterogeneous views of a post (i.e. representations encoding social patterns and semantic patterns), the discrimination is done by maximizing the mutual information between different  ...  Graph Neural Network can be categorized into two directions: the spectral-based approaches and the spatial-based approaches [36] .  ... 
arXiv:2204.08838v1 fatcat:ybmyd4ipxfh3zamwxcd53ha7k4

Multimodal Classification of Violent Online Political Extremism Content with Graph Convolutional Networks

Stevan Rudinac, Iva Gornishka, Marcel Worring
2017 Proceedings of the on Thematic Workshops of ACM Multimedia 2017 - Thematic Workshops '17  
Here we demonstrate the potential of using neural networks on graphs for classifying multimedia content and, perhaps more importantly, the effectiveness of multimedia analysis techniques in aiding the  ...  To integrate heterogeneous information extracted from the posts, i.e. text, visual content and the information about user interactions with the online platform, we deploy graph convolutional networks that  ...  Maura Conway from the Dublin City University for fruitful discussions about the qualitative analysis of violent online political extremism content.  ... 
doi:10.1145/3126686.3126776 dblp:conf/mm/RudinacGW17 fatcat:kxpmaws5yzeovijqlg57rsd3xe

A Machine Learning Pipeline to Examine Political Bias with Congressional Speeches [article]

Prasad hajare, Sadia Kamal, Siddharth Krishnan, Arunkumar Bagavathi
2021 arXiv   pre-print
Most of the current methods rely heavily on the manually-labeled ground-truth data for the underlying political bias prediction tasks.  ...  Computational methods to model political bias in social media involve several challenges due to heterogeneity, high-dimensional, multiple modalities, and the scale of the data.  ...  Neural network based approaches have been widely used in political bias detection and ideology detection problems in past years.  ... 
arXiv:2109.09014v1 fatcat:e6vwafinfrel7ellyygla7qfr4

LogicalFactChecker: Leveraging Logical Operations for Fact Checking with Graph Module Network [article]

Wanjun Zhong, Duyu Tang, Zhangyin Feng, Nan Duan, Ming Zhou, Ming Gong, Linjun Shou, Daxin Jiang, Jiahai Wang, Jian Yin
2020 arXiv   pre-print
This is achieved by a graph module network built upon the Transformer-based architecture.  ...  The graph is used to obtain graph-enhanced contextual representations of words in Transformer-based architecture.  ...  Figure 5 shows an example of a composed network based on the structure of the program.  ... 
arXiv:2004.13659v1 fatcat:gwsd5uihhja4rngarzw3jmm4gi

Fake News Detection through Graph Comment Advanced Learning [article]

Hao Liao, Qixin Liu, Kai Shu, Xing xie
2021 arXiv   pre-print
Thus, we model user-comment context through network representation learning based on heterogeneous graph neural network.  ...  Unlike conventional means which merely focus on either content or user comments, effective collaboration of heterogeneous social media information, including content and context factors of news, users'  ...  Part 2: Network representation learning based on heterogeneous graph neural network.  ... 
arXiv:2011.01579v2 fatcat:2dm5o47bznad7dyfcjx3iccqvy

A Comprehensive Survey on Community Detection with Deep Learning [article]

Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu
2021 arXiv   pre-print
This survey devises and proposes a new taxonomy covering different state-of-the-art methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep  ...  The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders.  ...  detection in complex network CON Conductance Detecting communities from heterogeneous graphs: A Context CP-GNN Context Path-based Graph Neural Network [92] path-based graph neural network model  ... 
arXiv:2105.12584v2 fatcat:matipshxnzcdloygrcrwx2sxr4

DKN: Deep Knowledge-Aware Network for News Recommendation [article]

Hongwei Wang, Fuzheng Zhang, Xing Xie, Minyi Guo
2018 arXiv   pre-print
The key component of DKN is a multi-channel and word-entity-aligned knowledge-aware convolutional neural network (KCNN) that fuses semantic-level and knowledge-level representations of news.  ...  To solve the above problems, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation.  ...  Note that except for LibFM, other baselines are all based on deep neural networks since we aim to compare our approach with state-of-the-art deep learning models.  ... 
arXiv:1801.08284v2 fatcat:c6p7njibivfsricpgrxin2nj2u

A multi-layer approach to disinformation detection on Twitter [article]

Francesco Pierri, Carlo Piccardi, Stefano Ceri
2020 arXiv   pre-print
to classify disinformation vs mainstream networks with high accuracy (AUROC up to 94%), also when considering the political bias of different sources in the classification task.  ...  We believe that our network-based approach provides useful insights which pave the way to the future development of a system to detect misleading and harmful information spreading on social media.  ...  based solely on the diffusion of news items on Twitter social platform.  ... 
arXiv:2002.12612v2 fatcat:t5sumqvubvbaraev36if5t25e4

Graph Neural Network: A Comprehensive Review on Non-Euclidean Space

Nurul A. Asif, Yeahia Sarker, Ripon K. Chakrabortty, Michael J. Ryan, Md. Hafiz Ahamed, Dip K. Saha, Faisal R. Badal, Sajal K. Das, Md. Firoz Ali, Sumaya I. Moyeen, Md. Robiul Islam, Zinat Tasneem
2021 IEEE Access  
Graph Neural Networks (GNNs) solve this problem by exploiting the relationships among graph data.  ...  of the future scope for the applications of graph models as well as highlight the limitations of existing graph networks.  ...  But these solutions are still in the preliminary stage as they only provided a new way of exploring graph-based networks.  ... 
doi:10.1109/access.2021.3071274 fatcat:yufufsrgqvgyzhxljgkmejuyhe

A Survey on Fairness for Machine Learning on Graphs [article]

Manvi Choudhary and Charlotte Laclau and Christine Largeron
2022 arXiv   pre-print
We also recall the different metrics proposed to evaluate potential bias at different levels of the graph mining process; then we provide a comprehensive overview of recent contributions in the domain  ...  It aims to present a comprehensive review of state-of-the-art techniques in fairness on graph mining and identify the open challenges and future trends.  ...  Graph Neural Networks based models Graph Neural Networks (GNN) models have recently established themselves as state-of-the-art for the graph-related downstream tasks.  ... 
arXiv:2205.05396v1 fatcat:t7nis5olbretdf3nwarsho5x5i

Attributed Multi-Relational Attention Network for Fact-checking URL Recommendation [article]

Di You, Nguyen Vo, Kyumin Lee, Qiang Liu
2020 arXiv   pre-print
In particular, our proposed framework consists of a multi-relational attentive module and a heterogeneous graph attention network to learn complex/semantic relationship between user-URL pairs, user-user  ...  To overcome these problems and complement existing methods against fake news, in this paper we propose a deep-learning based fact-checking URL recommender system to mitigate impact of fake news in social  ...  Any opinions, findings and conclusions or recommendations expressed in this material are the author(s) and do not necessarily reflect those of the sponsors.  ... 
arXiv:2001.02214v1 fatcat:rkylorousjcu3f7mdh34krbmq4

Survey of Generative Methods for Social Media Analysis [article]

Stan Matwin, Aristides Milios, Paweł Prałat, Amilcar Soares, François Théberge
2021 arXiv   pre-print
Networks, on the other hand, may capture various complex relationships providing additional insight and identifying important patterns that would otherwise go unnoticed.  ...  We included two important aspects that currently gain importance in mining and modeling social media: dynamics and networks.  ...  See [260, 242] for two sample comprehensive surveys (from the many available) on Graph Neural Networks (GNN).  ... 
arXiv:2112.07041v1 fatcat:xgmduwctpbddfo67y6ack5s2um

A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability [article]

Enyan Dai, Tianxiang Zhao, Huaisheng Zhu, Junjie Xu, Zhimeng Guo, Hui Liu, Jiliang Tang, Suhang Wang
2022 arXiv   pre-print
GNNs trained on social networks may embed the discrimination in their decision process, strengthening the undesirable societal bias.  ...  Graph Neural Networks (GNNs) have made rapid developments in the recent years.  ...  Extensive Heterogeneous Graph Neural Networks (HGNNs) have been investigated for heterogeneous graphs.  ... 
arXiv:2204.08570v1 fatcat:7c3pkxitrbhgxj6fytn6f3r644

A multi-layer approach to disinformation detection in US and Italian news spreading on Twitter

Francesco Pierri, Carlo Piccardi, Stefano Ceri
2020 EPJ Data Science  
We believe that our network-based approach provides useful insights which pave the way to the future development of a system to detect misleading and harmful information spreading on social media.  ...  AbstractWe tackle the problem of classifying news articles pertaining to disinformation vs mainstream news by solely inspecting their diffusion mechanisms on Twitter.  ...  F.P. is grateful to Manlio De Domenico and Riccardo Gallotti for insightful discussions on multi-layer networks.  ... 
doi:10.1140/epjds/s13688-020-00253-8 fatcat:kzowtgijq5aedjf3po7jpnnffu

Personalized News Recommendation: Methods and Challenges [article]

Chuhan Wu, Fangzhao Wu, Yongfeng Huang, Xing Xie
2022 arXiv   pre-print
Instead of following the conventional taxonomy of news recommendation methods, in this paper we propose a novel perspective to understand personalized news recommendation based on its core problems and  ...  We then discuss the key points on improving the responsibility of personalized news recommender systems. Finally, we raise several research directions that are worth investigating in the future.  ...  It uses the same architecture with DAN to learn text-based news representations, and uses a two-layer graph neural network (GNN) to learn graph-based news representations from a heterogeneous user-news-topic  ... 
arXiv:2106.08934v3 fatcat:iagqsw73hrehxaxpvpydvtr26m
« Previous Showing results 1 — 15 out of 1,567 results