arXiv - CS - Social and Information Networks最新文献_第3页

MAPX: An explainable model-agnostic framework for the detection of false information on social media networks MAPX：用于检测社交媒体网络虚假信息的可解释模型无关框架

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08522

Sarah Condran, Michael Bewong, Selasi Kwashie, Md Zahidul Islam, Irfan Altas, Joshua Condran

{"title":"MAPX: An explainable model-agnostic framework for the detection of false information on social media networks","authors":"Sarah Condran, Michael Bewong, Selasi Kwashie, Md Zahidul Islam, Irfan Altas, Joshua Condran","doi":"arxiv-2409.08522","DOIUrl":"https://doi.org/arxiv-2409.08522","url":null,"abstract":"The automated detection of false information has become a fundamental task in\u0000combating the spread of \"fake news\" on online social media networks (OSMN) as\u0000it reduces the need for manual discernment by individuals. In the literature,\u0000leveraging various content or context features of OSMN documents have been\u0000found useful. However, most of the existing detection models often utilise\u0000these features in isolation without regard to the temporal and dynamic changes\u0000oft-seen in reality, thus, limiting the robustness of the models. Furthermore,\u0000there has been little to no consideration of the impact of the quality of\u0000documents' features on the trustworthiness of the final prediction. In this\u0000paper, we introduce a novel model-agnostic framework, called MAPX, which allows\u0000evidence based aggregation of predictions from existing models in an\u0000explainable manner. Indeed, the developed aggregation method is adaptive,\u0000dynamic and considers the quality of OSMN document features. Further, we\u0000perform extensive experiments on benchmarked fake news datasets to demonstrate\u0000the effectiveness of MAPX using various real-world data quality scenarios. Our\u0000empirical results show that the proposed framework consistently outperforms all\u0000state-of-the-art models evaluated. For reproducibility, a demo of MAPX is\u0000available at href{https://github.com/SCondran/MAPX_framework}{this link}","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"104 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unveiling User Engagement Patterns on Stack Exchange Through Network Analysis 通过网络分析揭示用户在 Stack Exchange 上的参与模式

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08944

Agnik Saha, Mohammad Shahidul Kader, Mohammad Masum

引用次数: 0

Fusing Dynamics Equation: A Social Opinions Prediction Algorithm with LLM-based Agents 融合动力学方程：基于 LLM 代理的社会意见预测算法

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08717

Junchi Yao, Hongjie Zhang, Jie Ou, Dingyi Zuo, Zheng Yang, Zhicheng Dong

{"title":"Fusing Dynamics Equation: A Social Opinions Prediction Algorithm with LLM-based Agents","authors":"Junchi Yao, Hongjie Zhang, Jie Ou, Dingyi Zuo, Zheng Yang, Zhicheng Dong","doi":"arxiv-2409.08717","DOIUrl":"https://doi.org/arxiv-2409.08717","url":null,"abstract":"In the context where social media is increasingly becoming a significant\u0000platform for social movements and the formation of public opinion, accurately\u0000simulating and predicting the dynamics of user opinions is of great importance\u0000for understanding social phenomena, policy making, and guiding public opinion.\u0000However, existing simulation methods face challenges in capturing the\u0000complexity and dynamics of user behavior. Addressing this issue, this paper\u0000proposes an innovative simulation method for the dynamics of social media user\u0000opinions, the FDE-LLM algorithm, which incorporates opinion dynamics and\u0000epidemic model. This effectively constrains the actions and opinion evolution\u0000process of large language models (LLM), making them more aligned with the real\u0000cyber world. In particular, the FDE-LLM categorizes users into opinion leaders\u0000and followers. Opinion leaders are based on LLM role-playing and are\u0000constrained by the CA model, while opinion followers are integrated into a\u0000dynamic system that combines the CA model with the SIR model. This innovative\u0000design significantly improves the accuracy and efficiency of the simulation.\u0000Experiments were conducted on four real Weibo datasets and validated using the\u0000open-source model ChatGLM. The results show that, compared to traditional\u0000agent-based modeling (ABM) opinion dynamics algorithms and LLM-based opinion\u0000diffusion algorithms, our FDE-LLM algorithm demonstrates higher accuracy and\u0000interpretability.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sybil Detection using Graph Neural Networks 利用图神经网络检测假冒者

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08631

Stuart Heeb, Andreas Plesner, Roger Wattenhofer

{"title":"Sybil Detection using Graph Neural Networks","authors":"Stuart Heeb, Andreas Plesner, Roger Wattenhofer","doi":"arxiv-2409.08631","DOIUrl":"https://doi.org/arxiv-2409.08631","url":null,"abstract":"This paper presents SYBILGAT, a novel approach to Sybil detection in social\u0000networks using Graph Attention Networks (GATs). Traditional methods for Sybil\u0000detection primarily leverage structural properties of networks; however, they\u0000tend to struggle with a large number of attack edges and are often unable to\u0000simultaneously utilize both known Sybil and honest nodes. Our proposed method\u0000addresses these limitations by dynamically assigning attention weights to\u0000different nodes during aggregations, enhancing detection performance. We\u0000conducted extensive experiments in various scenarios, including pretraining in\u0000sampled subgraphs, synthetic networks, and networks under targeted attacks. The\u0000results show that SYBILGAT significantly outperforms the state-of-the-art\u0000algorithms, particularly in scenarios with high attack complexity and when the\u0000number of attack edges increases. Our approach shows robust performance across\u0000different network models and sizes, even as the detection task becomes more\u0000challenging. We successfully applied the model to a real-world Twitter graph\u0000with more than 269k nodes and 6.8M edges. The flexibility and generalizability\u0000of SYBILGAT make it a promising tool to defend against Sybil attacks in online\u0000social networks with only structural information.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"11 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Community Fact-Checks Trigger Moral Outrage in Replies to Misleading Posts on Social Media 社区事实核查引发道德愤怒，回应社交媒体上的误导性帖子

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08829

Yuwei Chuai, Anastasia Sergeeva, Gabriele Lenzini, Nicolas Pröllochs

{"title":"Community Fact-Checks Trigger Moral Outrage in Replies to Misleading Posts on Social Media","authors":"Yuwei Chuai, Anastasia Sergeeva, Gabriele Lenzini, Nicolas Pröllochs","doi":"arxiv-2409.08829","DOIUrl":"https://doi.org/arxiv-2409.08829","url":null,"abstract":"Displaying community fact-checks is a promising approach to reduce engagement\u0000with misinformation on social media. However, how users respond to misleading\u0000content emotionally after community fact-checks are displayed on posts is\u0000unclear. Here, we employ quasi-experimental methods to causally analyze changes\u0000in sentiments and (moral) emotions in replies to misleading posts following the\u0000display of community fact-checks. Our evaluation is based on a large-scale\u0000panel dataset comprising N=2,225,260 replies across 1841 source posts from X's\u0000Community Notes platform. We find that informing users about falsehoods through\u0000community fact-checks significantly increases negativity (by 7.3%), anger (by\u000013.2%), disgust (by 4.7%), and moral outrage (by 16.0%) in the corresponding\u0000replies. These results indicate that users perceive spreading misinformation as\u0000a violation of social norms and that those who spread misinformation should\u0000expect negative reactions once their content is debunked. We derive important\u0000implications for the design of community-based fact-checking systems.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Community-based fact-checking reduces the spread of misleading posts on social media 基于社区的事实核查减少了误导性帖子在社交媒体上的传播

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08781

Yuwei Chuai, Moritz Pilarski, Thomas Renault, David Restrepo-Amariles, Aurore Troussel-Clément, Gabriele Lenzini, Nicolas Pröllochs

{"title":"Community-based fact-checking reduces the spread of misleading posts on social media","authors":"Yuwei Chuai, Moritz Pilarski, Thomas Renault, David Restrepo-Amariles, Aurore Troussel-Clément, Gabriele Lenzini, Nicolas Pröllochs","doi":"arxiv-2409.08781","DOIUrl":"https://doi.org/arxiv-2409.08781","url":null,"abstract":"Community-based fact-checking is a promising approach to verify social media\u0000content and correct misleading posts at scale. Yet, causal evidence regarding\u0000its effectiveness in reducing the spread of misinformation on social media is\u0000missing. Here, we performed a large-scale empirical study to analyze whether\u0000community notes reduce the spread of misleading posts on X. Using a\u0000Difference-in-Differences design and repost time series data for N=237,677\u0000(community fact-checked) cascades that had been reposted more than 431 million\u0000times, we found that exposing users to community notes reduced the spread of\u0000misleading posts by, on average, 62.0%. Furthermore, community notes increased\u0000the odds that users delete their misleading posts by 103.4%. However, our\u0000findings also suggest that community notes might be too slow to intervene in\u0000the early (and most viral) stage of the diffusion. Our work offers important\u0000implications to enhance the effectiveness of community-based fact-checking\u0000approaches on social media.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"12 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimation of Graph Features Based on Random Walks Using Neighbors' Properties 基于随机漫步的图形特征估算（利用邻域属性

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08599

Tsuyoshi Hasegawa, Shiori Hironaka, Kazuyuki Shudo

引用次数: 0

DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation DELTA：带拓扑不确定性的双一致性迭代，用于主动图域自适应

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08946

Pengyun Wang, Yadi Cao, Chris Russell, Siyu Heng, Junyu Luo, Yanxin Shen, Xiao Luo

{"title":"DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation","authors":"Pengyun Wang, Yadi Cao, Chris Russell, Siyu Heng, Junyu Luo, Yanxin Shen, Xiao Luo","doi":"arxiv-2409.08946","DOIUrl":"https://doi.org/arxiv-2409.08946","url":null,"abstract":"Graph domain adaptation has recently enabled knowledge transfer across\u0000different graphs. However, without the semantic information on target graphs,\u0000the performance on target graphs is still far from satisfactory. To address the\u0000issue, we study the problem of active graph domain adaptation, which selects a\u0000small quantitative of informative nodes on the target graph for extra\u0000annotation. This problem is highly challenging due to the complicated\u0000topological relationships and the distribution discrepancy across graphs. In\u0000this paper, we propose a novel approach named Dual Consistency Delving with\u0000Topological Uncertainty (DELTA) for active graph domain adaptation. Our DELTA\u0000consists of an edge-oriented graph subnetwork and a path-oriented graph\u0000subnetwork, which can explore topological semantics from complementary\u0000perspectives. In particular, our edge-oriented graph subnetwork utilizes the\u0000message passing mechanism to learn neighborhood information, while our\u0000path-oriented graph subnetwork explores high-order relationships from\u0000substructures. To jointly learn from two subnetworks, we roughly select\u0000informative candidate nodes with the consideration of consistency across two\u0000subnetworks. Then, we aggregate local semantics from its K-hop subgraph based\u0000on node degrees for topological uncertainty estimation. To overcome potential\u0000distribution shifts, we compare target nodes and their corresponding source\u0000nodes for discrepancy scores as an additional component for fine selection.\u0000Extensive experiments on benchmark datasets demonstrate that DELTA outperforms\u0000various state-of-the-art approaches.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accurate and Fast Estimation of Temporal Motifs using Path Sampling 利用路径采样准确快速地估计时空动机

arXiv - CS - Social and Information Networks Pub Date : 2024-09-13 DOI: arxiv-2409.08975

Yunjie Pan, Omkar Bhalerao, C. Seshadhri, Nishil Talati

{"title":"Accurate and Fast Estimation of Temporal Motifs using Path Sampling","authors":"Yunjie Pan, Omkar Bhalerao, C. Seshadhri, Nishil Talati","doi":"arxiv-2409.08975","DOIUrl":"https://doi.org/arxiv-2409.08975","url":null,"abstract":"Counting the number of small subgraphs, called motifs, is a fundamental\u0000problem in social network analysis and graph mining. Many real-world networks\u0000are directed and temporal, where edges have timestamps. Motif counting in\u0000directed, temporal graphs is especially challenging because there are a\u0000plethora of different kinds of patterns. Temporal motif counts reveal much\u0000richer information and there is a need for scalable algorithms for motif\u0000counting. A major challenge in counting is that there can be trillions of temporal\u0000motif matches even with a graph with only millions of vertices. Both the motifs\u0000and the input graphs can have multiple edges between two vertices, leading to a\u0000combinatorial explosion problem. Counting temporal motifs involving just four\u0000vertices is not feasible with current state-of-the-art algorithms. We design an algorithm, TEACUPS, that addresses this problem using a novel\u0000technique of temporal path sampling. We combine a path sampling method with\u0000carefully designed temporal data structures, to propose an efficient\u0000approximate algorithm for temporal motif counting. TEACUPS is an unbiased\u0000estimator with provable concentration behavior, which can be used to bound the\u0000estimation error. For a Bitcoin graph with hundreds of millions of edges,\u0000TEACUPS runs in less than 1 minute, while the exact counting algorithm takes\u0000more than a day. We empirically demonstrate the accuracy of TEACUPS on large\u0000datasets, showing an average of 30$times$ speedup (up to 2000$times$ speedup)\u0000compared to existing GPU-based exact counting methods while preserving high\u0000count estimation accuracy.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"52 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Informal Labor of Content Creators: Situating Xiaohongshu's Key Opinion Consumers in Relationships to Marketers, Consumer Brands, and the Platform 内容创作者的非正式劳动：小红书关键意见消费者与营销者、消费品牌和平台的关系定位

arXiv - CS - Social and Information Networks Pub Date : 2024-09-12 DOI: arxiv-2409.08360

Huiran Yi, Lu Xian

{"title":"The Informal Labor of Content Creators: Situating Xiaohongshu's Key Opinion Consumers in Relationships to Marketers, Consumer Brands, and the Platform","authors":"Huiran Yi, Lu Xian","doi":"arxiv-2409.08360","DOIUrl":"https://doi.org/arxiv-2409.08360","url":null,"abstract":"This paper critically examines flexible content creation conducted by Key\u0000Opinion Consumers (KOCs) on a prominent social media and e-commerce platform in\u0000China, Xiaohongshu (RED). Drawing on nine-month ethnographic work conducted\u0000online, we find that the production of the KOC role on RED is predicated on the\u0000interactions and negotiations among multiple stakeholders -- content creators,\u0000marketers, consumer brands (corporations), and the platform. KOCs are\u0000instrumental in RED influencer marketing tactics and amplify the mundane and\u0000daily life content popular on the platform. They navigate the dynamics in the\u0000triangulated relations with other stakeholders in order to secure economic\u0000opportunities for producing advertorial content, and yet, the labor involved in\u0000producing such content is deliberately obscured to make it appear as\u0000spontaneous, ordinary user posts for the sake of marketing campaigns.\u0000Meanwhile, the commercial value of their work is often underestimated and\u0000overshadowed in corporate paperwork, platform technological mechanisms, and\u0000business models, resulting in and reinforcing inadequate recognition and\u0000compensation of KOCs. We propose the concept of ``informal labor'' to offer a\u0000new lens to understand content creation labor that is indispensable yet\u0000unrecognized by the social media industry. We advocate for a contextualized and\u0000nuanced examination of how labor is valued and compensated and urge for better\u0000protections and working conditions for informal laborers like KOCs.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":"10 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142263485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0