Pub Date : 2024-02-14DOI: 10.1109/TCSS.2024.3357696
Jing Yang;Laurence T. Yang;Hao Wang;Yuan Gao
Global news events graphs (GNEG) are designed for the noisy and ungrammatical world's news media, aiming at capturing the true insight and providing explanations by incorporating potential dimensions and network structures of global news. This article focuses on the temporal representation learning of GNEG to eliminate misunderstanding or ambiguity caused by missing information. Although some temporal models have been developed, the crossover interactions among entity, relation, and time have not been explicitly discussed. The multidirectional effects between entities, relations, and timestamps matter in predicting the establishment of quadruples. This motivates the proposal of learning temporal interaction embeddings (TIE) to benefit GNEG link prediction performance. Specifically, we propose the following. 1) We propose a crossover convolution layer to learn the two-by-two and common interaction features of entity, relation, and time in GNEG to capture their potential effect patterns in the context of different quadruples. 2) For the learned interaction information, we adopt tensor neural network (TNN) to maintain the multiple order structure and further extract effective features to improve prediction. 3) A tensor temporal consistency constraint (TCC) is proposed to enhance the learning of time-weakly sensitive information and induce the embeddings to have a certain compatibility over time. Finally, we carried out extensive experiments on three benchmark datasets, the results proved that the performance of the proposed TIE model is competitive with the state-of-the-art methods.
{"title":"Temporal Interaction Embedding for Link Prediction in Global News Event Graph","authors":"Jing Yang;Laurence T. Yang;Hao Wang;Yuan Gao","doi":"10.1109/TCSS.2024.3357696","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3357696","url":null,"abstract":"Global news events graphs (GNEG) are designed for the noisy and ungrammatical world's news media, aiming at capturing the true insight and providing explanations by incorporating potential dimensions and network structures of global news. This article focuses on the temporal representation learning of GNEG to eliminate misunderstanding or ambiguity caused by missing information. Although some temporal models have been developed, the crossover interactions among entity, relation, and time have not been explicitly discussed. The multidirectional effects between entities, relations, and timestamps matter in predicting the establishment of quadruples. This motivates the proposal of learning temporal interaction embeddings (TIE) to benefit GNEG link prediction performance. Specifically, we propose the following. 1) We propose a crossover convolution layer to learn the two-by-two and common interaction features of entity, relation, and time in GNEG to capture their potential effect patterns in the context of different quadruples. 2) For the learned interaction information, we adopt tensor neural network (TNN) to maintain the multiple order structure and further extract effective features to improve prediction. 3) A tensor temporal consistency constraint (TCC) is proposed to enhance the learning of time-weakly sensitive information and induce the embeddings to have a certain compatibility over time. Finally, we carried out extensive experiments on three benchmark datasets, the results proved that the performance of the proposed TIE model is competitive with the state-of-the-art methods.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-13DOI: 10.1109/TCSS.2024.3359010
Zeinab Noorian;Amira Ghenai;Hadiseh Moradisani;Fattane Zarrinkalam;Soroush Zamani Alavijeh
Hate speech in social media is a growing problem that reinforces racial discrimination and mistrust between people, leading to physical crimes, violence, and fragmentation in world communities. Although previous studies showed the potential of user profiling in hate speech detection in social media, there has not been a thorough analysis of users’ characteristics and dispositions to understand the development of hate attitudes among users. To bridge this gap, we investigate the role of a wide range of psycholinguistic and behavioral traits in characterizing and distinguishing users prone to post hate speech on social media. Considering anti-Asian hate during the COVID-19 pandemic as a case study, we curate a dataset of 5 417 041 tweets from 3001 Twitter users prone to publish hate content (aka hateful-to-be users) and a corresponding matched set of 3001 control users. Our findings reveal significant statistical differences in most dimensions of psycholinguistic attributes and online activities of hateful-to-be users compared to control users. We further develop a classifier and demonstrate that features derived from user timelines are strong indicators for automatically predicting the onset of hateful behavior.
{"title":"User-Centric Modeling of Online Hate Through the Lens of Psycholinguistic Patterns and Behaviors in Social Media","authors":"Zeinab Noorian;Amira Ghenai;Hadiseh Moradisani;Fattane Zarrinkalam;Soroush Zamani Alavijeh","doi":"10.1109/TCSS.2024.3359010","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3359010","url":null,"abstract":"Hate speech in social media is a growing problem that reinforces racial discrimination and mistrust between people, leading to physical crimes, violence, and fragmentation in world communities. Although previous studies showed the potential of user profiling in hate speech detection in social media, there has not been a thorough analysis of users’ characteristics and dispositions to understand the development of hate attitudes among users. To bridge this gap, we investigate the role of a wide range of psycholinguistic and behavioral traits in characterizing and distinguishing users prone to post hate speech on social media. Considering anti-Asian hate during the COVID-19 pandemic as a case study, we curate a dataset of 5 417 041 tweets from 3001 Twitter users prone to publish hate content (aka hateful-to-be users) and a corresponding matched set of 3001 control users. Our findings reveal significant statistical differences in most dimensions of psycholinguistic attributes and online activities of hateful-to-be users compared to control users. We further develop a classifier and demonstrate that features derived from user timelines are strong indicators for automatically predicting the onset of hateful behavior.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-13DOI: 10.1109/TCSS.2024.3360618
Jian Shu;Yao Liang;Wanli Ma;Linlan Liu
Evaluation of key nodes is a hot issue in social networks. Existing research primarily evaluates the importance of nodes in social networks based on centrality metrics, neglecting the node’s own attributes. After analyzing the topology attributes and the basic attributes of nodes, this article proposes a key nodes evaluation method for social networks, which is based on analytic hierarchy process (AHP) and improved Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR), termed AE-VIKOR. Considering global attributes, local attributes, and positional attributes of nodes, three evaluation metrics are constructed. The subjective and objective weights are computed by AHP and entropy weight method, respectively. The comprehensive weights of metrics are determined by combination weighting method based on square sums of distance. Due to the excessive weight of specific metrics and excessive difference in data distribution, the computation of individual regret value depends too much on a single metric in VIKOR method, individual regret value is optimized by weighted sum of closeness between the scheme to be evaluated and the negative ideal scheme. Multimetric evaluation schemes are ranked to achieve the evaluation of key nodes. Experiments on two real social network datasets show that the key nodes evaluated by AE-VIKOR have stronger information spread ability and more fans than the ones of the existing methods. In addition, the validity of the three metrics and the two improvements on the VIKOR method are verified by ablation experiments.
{"title":"Key Nodes Evaluation Method Based on Combination Weighting VIKOR in Social Networks","authors":"Jian Shu;Yao Liang;Wanli Ma;Linlan Liu","doi":"10.1109/TCSS.2024.3360618","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3360618","url":null,"abstract":"Evaluation of key nodes is a hot issue in social networks. Existing research primarily evaluates the importance of nodes in social networks based on centrality metrics, neglecting the node’s own attributes. After analyzing the topology attributes and the basic attributes of nodes, this article proposes a key nodes evaluation method for social networks, which is based on analytic hierarchy process (AHP) and improved Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR), termed AE-VIKOR. Considering global attributes, local attributes, and positional attributes of nodes, three evaluation metrics are constructed. The subjective and objective weights are computed by AHP and entropy weight method, respectively. The comprehensive weights of metrics are determined by combination weighting method based on square sums of distance. Due to the excessive weight of specific metrics and excessive difference in data distribution, the computation of individual regret value depends too much on a single metric in VIKOR method, individual regret value is optimized by weighted sum of closeness between the scheme to be evaluated and the negative ideal scheme. Multimetric evaluation schemes are ranked to achieve the evaluation of key nodes. Experiments on two real social network datasets show that the key nodes evaluated by AE-VIKOR have stronger information spread ability and more fans than the ones of the existing methods. In addition, the validity of the three metrics and the two improvements on the VIKOR method are verified by ablation experiments.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The impressive development of facial manipulation techniques has raised severe public concerns. Identity-aware methods, especially suitable for protecting celebrities, are seen as one of promising face forgery detection approaches with additional reference video. However, without in-depth observation of fake video's characteristics, most existing identity-aware algorithms are just naive imitation of face verification model and fail to exploit discriminative information. In this article, we argue that it is necessary to take both spatial and temporal perspectives into consideration for adequate inconsistency clues and propose a novel forgery detector named SpatioTemporal IDentity network (STIDNet). To effectively capture heterogeneous spatiotemporal information in a unified formulation, our STIDNet is following a knowledge distillation architecture that the student identity extractor receives supervision from a spatial information encoder (SIE) and a temporal information encoder (TIE) through multiteacher training. Specifically, a regional sensitive identity modeling paradigm is proposed in SIE by introducing facial blending augmentation but with uniform identity label, thus encourage model to focus on spatial discriminative region like outer face. Meanwhile, considering the strong temporal correlation between audio and talking face video, our TIE is devised in a cross-modal pattern that the audio information is introduced to supervise model exploiting temporal personalized movements. Benefit from knowledge transfer from SIE and TIE, STIDNet is able to capture individual's essential spatiotemporal identity attributes and sensitive to even subtle identity deviation caused by manipulation. Extensive experiments indicate the superiority of our STIDNet compared with previous works. Moreover, we also demonstrate STIDNet is more suitable for real-world implementation in terms of model complexity and reference set size.
面部伪造技术的迅猛发展引起了公众的严重关切。身份感知方法,尤其是适用于保护名人的身份感知方法,被认为是一种通过附加参考视频进行人脸伪造检测的有前途的方法。然而,由于缺乏对伪造视频特征的深入观察,大多数现有的身份感知算法只是对人脸验证模型的天真模仿,无法利用鉴别信息。在这篇文章中,我们认为有必要从空间和时间两个角度来获取足够的不一致线索,并提出了一种名为 "时空身份识别网络(STIDNet)"的新型伪造检测器。为了以统一的表述有效捕捉异构时空信息,我们的 STIDNet 采用了知识提炼架构,即学生身份提取器通过多教师训练接受空间信息编码器(SIE)和时间信息编码器(TIE)的监督。具体来说,在 SIE 中提出了一种区域敏感的身份建模范式,即通过引入面部混合增强但统一身份标签,从而鼓励模型将注意力集中在外侧面部等空间分辨区域。同时,考虑到音频和人脸视频之间存在很强的时间相关性,我们的 TIE 采用了跨模态模式,即引入音频信息来监督利用时间个性化运动的模型。得益于 SIE 和 TIE 的知识转移,STIDNet 能够捕捉个人的基本时空身份属性,并对操纵造成的细微身份偏差保持敏感。大量实验表明,与之前的研究相比,我们的 STIDNet 更具优势。此外,我们还证明 STIDNet 在模型复杂度和参考集大小方面更适合实际应用。
{"title":"STIDNet: Identity-Aware Face Forgery Detection With Spatiotemporal Knowledge Distillation","authors":"Mingqi Fang;Lingyun Yu;Hongtao Xie;Qingfeng Tan;Zhiyuan Tan;Amir Hussain;Zezheng Wang;Jiahong Li;Zhihong Tian","doi":"10.1109/TCSS.2024.3356549","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3356549","url":null,"abstract":"The impressive development of facial manipulation techniques has raised severe public concerns. Identity-aware methods, especially suitable for protecting celebrities, are seen as one of promising face forgery detection approaches with additional reference video. However, without in-depth observation of fake video's characteristics, most existing identity-aware algorithms are just naive imitation of face verification model and fail to exploit discriminative information. In this article, we argue that it is necessary to take both spatial and temporal perspectives into consideration for adequate inconsistency clues and propose a novel forgery detector named SpatioTemporal IDentity network (STIDNet). To effectively capture heterogeneous spatiotemporal information in a unified formulation, our STIDNet is following a knowledge distillation architecture that the student identity extractor receives supervision from a spatial information encoder (SIE) and a temporal information encoder (TIE) through multiteacher training. Specifically, a regional sensitive identity modeling paradigm is proposed in SIE by introducing facial blending augmentation but with uniform identity label, thus encourage model to focus on spatial discriminative region like outer face. Meanwhile, considering the strong temporal correlation between audio and talking face video, our TIE is devised in a cross-modal pattern that the audio information is introduced to supervise model exploiting temporal personalized movements. Benefit from knowledge transfer from SIE and TIE, STIDNet is able to capture individual's essential spatiotemporal identity attributes and sensitive to even subtle identity deviation caused by manipulation. Extensive experiments indicate the superiority of our STIDNet compared with previous works. Moreover, we also demonstrate STIDNet is more suitable for real-world implementation in terms of model complexity and reference set size.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-12DOI: 10.1109/TCSS.2024.3359254
Yuzi Yi;Nafei Zhu;Jingsha He;Anca Delia Jurcut;Xiangjun Ma;Yehong Luo
Privacy inference poses a significant threat to users of online social networks (OSNs). To deal with this issue, a number of privacy-enhancing technologies have been proposed with the goal of achieving a balance between the protection of privacy and the utility of data. Previous studies, however, failed to take into consideration the impact of the interdependency of privacy (IoP), which dictates that privacy decisions made by some users may affect the privacy of some other users. The implication of IoP is that too much privacy may be disclosed when multiple individuals share data with the same data accessor because privacy conflicts resulting from independent privacy decisions would make it possible for adversaries to infer the privacy of the target user. Ideally, cooperation that preserves privacy should allow OSN users to respect each other’s privacy specifications so as to resolve such privacy conflicts caused by independent privacy decisions of individuals. To facilitate the design, we propose a privacy-preserving cooperation framework based on the evolutionary game theory to facilitate such cooperation. Based on the framework, the dynamics of user strategies regarding whether to participate in the cooperation are analyzed and an evolutionary stable state is derived to serve as the basis for incentivizing users to participate in cooperative privacy protection. Experiments based on real OSN data show that the proposed cooperation framework is effective in modeling the behaviors of users and that the proposed incentive allocation method can incentivize users to participate in the cooperation. The proposed cooperation framework can not only helps lower the threat to user privacy resulting from privacy inference by data accessors but also allows OSN service providers to design effective privacy protection policies.
隐私推断对在线社交网络(OSN)用户构成了重大威胁。为了解决这个问题,人们提出了许多隐私增强技术,目的是在保护隐私和数据实用性之间实现平衡。然而,以往的研究没有考虑到隐私相互依赖(IoP)的影响,即一些用户做出的隐私决定可能会影响到其他一些用户的隐私。IoP 的含义是,当多人与同一数据访问者共享数据时,可能会泄露过多隐私,因为独立隐私决策导致的隐私冲突会使对手有可能推断出目标用户的隐私。理想情况下,保护隐私的合作应允许 OSN 用户相互尊重对方的隐私规范,以解决因个人独立隐私决策而产生的隐私冲突。为了便于设计,我们提出了一个基于进化博弈论的隐私保护合作框架,以促进这种合作。基于该框架,我们分析了用户是否参与合作的策略动态,并得出了一种进化稳定状态,作为激励用户参与合作保护隐私的基础。基于真实 OSN 数据的实验表明,所提出的合作框架能有效地模拟用户行为,所提出的激励分配方法能激励用户参与合作。所提出的合作框架不仅有助于降低数据访问者的隐私推断对用户隐私造成的威胁,还能让 OSN 服务提供商设计出有效的隐私保护政策。
{"title":"An Evolutionary Game Theory-Based Cooperation Framework for Countering Privacy Inference Attacks","authors":"Yuzi Yi;Nafei Zhu;Jingsha He;Anca Delia Jurcut;Xiangjun Ma;Yehong Luo","doi":"10.1109/TCSS.2024.3359254","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3359254","url":null,"abstract":"Privacy inference poses a significant threat to users of online social networks (OSNs). To deal with this issue, a number of privacy-enhancing technologies have been proposed with the goal of achieving a balance between the protection of privacy and the utility of data. Previous studies, however, failed to take into consideration the impact of the interdependency of privacy (IoP), which dictates that privacy decisions made by some users may affect the privacy of some other users. The implication of IoP is that too much privacy may be disclosed when multiple individuals share data with the same data accessor because privacy conflicts resulting from independent privacy decisions would make it possible for adversaries to infer the privacy of the target user. Ideally, cooperation that preserves privacy should allow OSN users to respect each other’s privacy specifications so as to resolve such privacy conflicts caused by independent privacy decisions of individuals. To facilitate the design, we propose a privacy-preserving cooperation framework based on the evolutionary game theory to facilitate such cooperation. Based on the framework, the dynamics of user strategies regarding whether to participate in the cooperation are analyzed and an evolutionary stable state is derived to serve as the basis for incentivizing users to participate in cooperative privacy protection. Experiments based on real OSN data show that the proposed cooperation framework is effective in modeling the behaviors of users and that the proposed incentive allocation method can incentivize users to participate in the cooperation. The proposed cooperation framework can not only helps lower the threat to user privacy resulting from privacy inference by data accessors but also allows OSN service providers to design effective privacy protection policies.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of social network to model the evolution of credit scores of networked enterprises is still a challenging task. This article develops an opinion dynamics model of the evolution of credit scores of enterprises in a social network. Firstly, based on the number of potential cooperated enterprises and the initial credit scores, the leader and follower enterprises are identified. Then, taking into consideration the cooperated benefit and discrimination cost, the cooperated utility between any two enterprises is calculated, which is used to compute the weights that one enterprise assigns to other enterprises. An opinion dynamics model on the evolution of credit scores of enterprises, inspired on the classical Friedkin–Johnsen’s social network model, is developed. Some desirable properties of the proposed opinion dynamics model are theoretically stated and proved. Finally, a numerical example is provided to illustrate the feasibility of the proposed opinion dynamics model, while a simulation analysis to investigate the joint influences of the connection probabilities and the network structure on the evolution of credit scores of enterprises is reported.
{"title":"Evolution of Credit Scores of Enterprises in a Social Network: A Perspective Based on Opinion Dynamics","authors":"Haiming Liang;Weijun Xu;Francisco Chiclana;Shui Yu;Yucheng Dong;Enrique Enrique Herrera-Viedma","doi":"10.1109/TCSS.2023.3324558","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3324558","url":null,"abstract":"The use of social network to model the evolution of credit scores of networked enterprises is still a challenging task. This article develops an opinion dynamics model of the evolution of credit scores of enterprises in a social network. Firstly, based on the number of potential cooperated enterprises and the initial credit scores, the leader and follower enterprises are identified. Then, taking into consideration the cooperated benefit and discrimination cost, the cooperated utility between any two enterprises is calculated, which is used to compute the weights that one enterprise assigns to other enterprises. An opinion dynamics model on the evolution of credit scores of enterprises, inspired on the classical Friedkin–Johnsen’s social network model, is developed. Some desirable properties of the proposed opinion dynamics model are theoretically stated and proved. Finally, a numerical example is provided to illustrate the feasibility of the proposed opinion dynamics model, while a simulation analysis to investigate the joint influences of the connection probabilities and the network structure on the evolution of credit scores of enterprises is reported.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141326275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fake news is a prevalent issue in modern society, leading to misinformation, and societal harm. News credibility assessment is a crucial approach for evaluating the accuracy and authenticity of news. It plays a significant role in enhancing public awareness and understanding of news, while also effectively mitigating the dissemination of fake news. However, news credibility assessment meets challenges when processing large-scale and constantly growing data, due to insufficient and unreliable labels and standards, and diversity and semantic ambiguity of news contents. Recently, machine learning models have been well developed to address these issues, but suffer from limited effectiveness. A unified framework is also required for them to represent various entities and relationships involved in news stories. This article proposes an entity ontology-based knowledge graph network (EKNet) to leverage knowledge graphs and entity frameworks for news credibility assessment. The model utilizes the information from knowledge graphs by combining entities and relationships from news and knowledge graphs. Experimental results show that the EKNet has advantages in evaluating news credibility over existing methods. Specifically, compared to several strong baselines, the model demonstrates a significant performance improvement in scores across various tasks. Which indicates that using the EKNet to address the challenges in news credibility assessment is highly effective and can conduct better performance for the problem of fake news in the social media environment.
{"title":"An Entity Ontology-Based Knowledge Graph Embedding Approach to News Credibility Assessment","authors":"Qi Liu;Yuanyuan Jin;Xuefei Cao;Xiaodong Liu;Xiaokang Zhou;Yonghong Zhang;Xiaolong Xu;Lianyong Qi","doi":"10.1109/TCSS.2023.3342873","DOIUrl":"https://doi.org/10.1109/TCSS.2023.3342873","url":null,"abstract":"Fake news is a prevalent issue in modern society, leading to misinformation, and societal harm. News credibility assessment is a crucial approach for evaluating the accuracy and authenticity of news. It plays a significant role in enhancing public awareness and understanding of news, while also effectively mitigating the dissemination of fake news. However, news credibility assessment meets challenges when processing large-scale and constantly growing data, due to insufficient and unreliable labels and standards, and diversity and semantic ambiguity of news contents. Recently, machine learning models have been well developed to address these issues, but suffer from limited effectiveness. A unified framework is also required for them to represent various entities and relationships involved in news stories. This article proposes an entity ontology-based knowledge graph network (EKNet) to leverage knowledge graphs and entity frameworks for news credibility assessment. The model utilizes the information from knowledge graphs by combining entities and relationships from news and knowledge graphs. Experimental results show that the EKNet has advantages in evaluating news credibility over existing methods. Specifically, compared to several strong baselines, the model demonstrates a significant performance improvement in scores across various tasks. Which indicates that using the EKNet to address the challenges in news credibility assessment is highly effective and can conduct better performance for the problem of fake news in the social media environment.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-09DOI: 10.1109/TCSS.2024.3355300
Asma Sormeily;Sajjad Dadkhah;Xichen Zhang;Ali A. Ghorbani
Alongside social media platforms’ rise in popularity, fake news circulation has increased, highlighting the need for more practical methods to detect this phenomenon. The constantly evolving format of fake news makes it difficult for approaches that rely on a single modality of news to generalize the different types of false news. Furthermore, earlier approaches require extensive propagation data to determine the veracity of news, which can be challenging to collect in the early stages of news dissemination. Thus, we propose a multimodal early fake news detection approach that leverages latent insights into both news content and propagation knowledge. We design a multimodule architecture using graph neural networks (GNNs) to represent edge-enhanced and node-enhanced propagation graphs and bidirectional encoder representations from transformers (BERTs) to generate contextualized representations of news content. Our approach tackles the challenge of early detection in a more realistic scenario, accessing early propagation data in a single social media post and short-length news content. Moreover, we conduct comprehensive studies on user characteristics using statistical techniques to identify attributes with strong discriminative capability for identifying false news. We also analyze temporal and structural properties of fake news propagation graphs to demonstrate distinguishable patterns of false and real news behavior. Our model outperforms several state-of-the-art methods, achieving an impressive F1-score of 99% and 96% on two public datasets. The individual contribution of various components in our model to the final performance is also measured, which can be insightful for future research on multimodal false news detection.
随着社交媒体平台的普及,虚假新闻的传播量也在不断增加,这就凸显出我们需要更实用的方法来检测这一现象。由于假新闻的形式不断变化,依赖于单一新闻模式的方法很难归纳出不同类型的假新闻。此外,早期的方法需要大量的传播数据来确定新闻的真实性,而在新闻传播的早期阶段收集这些数据具有挑战性。因此,我们提出了一种多模态早期假新闻检测方法,利用对新闻内容和传播知识的潜在洞察力。我们设计了一种多模块架构,利用图神经网络(GNN)来表示边缘增强和节点增强的传播图,并利用变压器的双向编码器表示法(BERT)来生成新闻内容的上下文表示法。我们的方法在更现实的场景中应对早期检测的挑战,在单个社交媒体帖子和短篇新闻内容中获取早期传播数据。此外,我们还利用统计技术对用户特征进行了全面研究,以确定在识别虚假新闻方面具有较强鉴别能力的属性。我们还分析了虚假新闻传播图的时间和结构属性,以展示虚假新闻和真实新闻行为的可区分模式。我们的模型优于几种最先进的方法,在两个公共数据集上分别取得了 99% 和 96% 的惊人 F1 分数。我们还测量了模型中各个组成部分对最终性能的贡献,这对未来多模态虚假新闻检测的研究很有启发。
{"title":"MEFaND: A Multimodel Framework for Early Fake News Detection","authors":"Asma Sormeily;Sajjad Dadkhah;Xichen Zhang;Ali A. Ghorbani","doi":"10.1109/TCSS.2024.3355300","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3355300","url":null,"abstract":"Alongside social media platforms’ rise in popularity, fake news circulation has increased, highlighting the need for more practical methods to detect this phenomenon. The constantly evolving format of fake news makes it difficult for approaches that rely on a single modality of news to generalize the different types of false news. Furthermore, earlier approaches require extensive propagation data to determine the veracity of news, which can be challenging to collect in the early stages of news dissemination. Thus, we propose a multimodal early fake news detection approach that leverages latent insights into both news content and propagation knowledge. We design a multimodule architecture using graph neural networks (GNNs) to represent edge-enhanced and node-enhanced propagation graphs and bidirectional encoder representations from transformers (BERTs) to generate contextualized representations of news content. Our approach tackles the challenge of early detection in a more realistic scenario, accessing early propagation data in a single social media post and short-length news content. Moreover, we conduct comprehensive studies on user characteristics using statistical techniques to identify attributes with strong discriminative capability for identifying false news. We also analyze temporal and structural properties of fake news propagation graphs to demonstrate distinguishable patterns of false and real news behavior. Our model outperforms several state-of-the-art methods, achieving an impressive F1-score of 99% and 96% on two public datasets. The individual contribution of various components in our model to the final performance is also measured, which can be insightful for future research on multimodal false news detection.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":4.5,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141993930","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-08DOI: 10.1109/TCSS.2024.3358176
Xuan Liu;Lu Liu;Yong Yuan;Yong-Hong Long;San-Xi Li;Fei-Yue Wang
Recent years have witnessed remarkable developments and increasingly deepened integrations between blockchain as a decentralized computing architecture and auction as an efficient resource allocation approach. Typically, blockchain can help provide a secured and trusted distributed environment for various auction scenarios, while auction is particularly suitable for designing resource allocation and pricing mechanisms in blockchain systems. As such, integrative research on blockchain and auction developed rapidly and attracted widespread attention in various fields ranging from academia to financial, industrial, and social services. However, a comprehensive survey on this interdisciplinary topic is still nonexistent, which motivates our work. In this article, we aim to fill this important research gap by reviewing the related literature. We first conducted a brief overview of blockchain technology and auction theory, and then systematically discussed the research progress on the existing blockchain research based on auction theory as well as auction research enabled by blockchain. Toward the end, we presented several open research issues and directions, aiming to provide useful guidance and reference for future research efforts.
{"title":"When Blockchain Meets Auction: A Comprehensive Survey","authors":"Xuan Liu;Lu Liu;Yong Yuan;Yong-Hong Long;San-Xi Li;Fei-Yue Wang","doi":"10.1109/TCSS.2024.3358176","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3358176","url":null,"abstract":"Recent years have witnessed remarkable developments and increasingly deepened integrations between blockchain as a decentralized computing architecture and auction as an efficient resource allocation approach. Typically, blockchain can help provide a secured and trusted distributed environment for various auction scenarios, while auction is particularly suitable for designing resource allocation and pricing mechanisms in blockchain systems. As such, integrative research on blockchain and auction developed rapidly and attracted widespread attention in various fields ranging from academia to financial, industrial, and social services. However, a comprehensive survey on this interdisciplinary topic is still nonexistent, which motivates our work. In this article, we aim to fill this important research gap by reviewing the related literature. We first conducted a brief overview of blockchain technology and auction theory, and then systematically discussed the research progress on the existing blockchain research based on auction theory as well as auction research enabled by blockchain. Toward the end, we presented several open research issues and directions, aiming to provide useful guidance and reference for future research efforts.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-07DOI: 10.1109/TCSS.2024.3355780
Daohan Su;Bowen Fan;Zhi Zhang;Haoyan Fu;Zhida Qin
Diversified recommendation systems have gained increasing popularity in recent years. Nowadays, the emerged graph neural networks (GNNs) have been used to improve the diversity performance. Although some progresses have been made, existing works purely focus on the user–item interactions and overlook the category information, which limits the capability to capture complex diversification among users or items and leads to poor performance. In this article, our target is to integrate full category information into user and item embeddings. To this end, we propose a diversified GNN-based recommendation systems diversified graph recommendation with contrastive learning (DCL). Specifically, we design three key components in our model: 1) the user–item interaction with category-related sampling enhances the interaction of unpopular items; 2) contrastive learning between users and categories shortens the distance of representations between users and their uninteracted categories; and 3) contrastive learning between items and categories diverges the distance of representations between items and their corresponding categories. By applying these three modules, we build a multitask training framework to achieve a balance between accuracy and diversity. Experiments on real-world datasets show that our proposed DCL achieves optimal diversity while paying a little price for accuracy.
{"title":"DCL: Diversified Graph Recommendation With Contrastive Learning","authors":"Daohan Su;Bowen Fan;Zhi Zhang;Haoyan Fu;Zhida Qin","doi":"10.1109/TCSS.2024.3355780","DOIUrl":"https://doi.org/10.1109/TCSS.2024.3355780","url":null,"abstract":"Diversified recommendation systems have gained increasing popularity in recent years. Nowadays, the emerged graph neural networks (GNNs) have been used to improve the diversity performance. Although some progresses have been made, existing works purely focus on the user–item interactions and overlook the category information, which limits the capability to capture complex diversification among users or items and leads to poor performance. In this article, our target is to integrate full category information into user and item embeddings. To this end, we propose a diversified GNN-based recommendation systems diversified graph recommendation with contrastive learning (DCL). Specifically, we design three key components in our model: 1) the user–item interaction with category-related sampling enhances the interaction of unpopular items; 2) contrastive learning between users and categories shortens the distance of representations between users and their uninteracted categories; and 3) contrastive learning between items and categories diverges the distance of representations between items and their corresponding categories. By applying these three modules, we build a multitask training framework to achieve a balance between accuracy and diversity. Experiments on real-world datasets show that our proposed DCL achieves optimal diversity while paying a little price for accuracy.","PeriodicalId":13044,"journal":{"name":"IEEE Transactions on Computational Social Systems","volume":null,"pages":null},"PeriodicalIF":5.0,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141319659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}