arXiv - CS - Social and Information Networks最新文献_第7页

Incorporating Like-Minded Peers to Overcome Friend Data Sparsity in Session-Based Social Recommendations 在基于会话的社交推荐中纳入志同道合的同伴，克服好友数据稀缺问题

arXiv - CS - Social and Information Networks Pub Date : 2024-09-04 DOI: arxiv-2409.02702

Chunyan An, Yunhan Li, Qiang Yang, Winston K. G. Seah, Zhixu Li, Conghao Yanga

{"title":"Incorporating Like-Minded Peers to Overcome Friend Data Sparsity in Session-Based Social Recommendations","authors":"Chunyan An, Yunhan Li, Qiang Yang, Winston K. G. Seah, Zhixu Li, Conghao Yanga","doi":"arxiv-2409.02702","DOIUrl":"https://doi.org/arxiv-2409.02702","url":null,"abstract":"Session-based Social Recommendation (SSR) leverages social relationships\u0000within online networks to enhance the performance of Session-based\u0000Recommendation (SR). However, existing SSR algorithms often encounter the\u0000challenge of ``friend data sparsity''. Moreover, significant discrepancies can\u0000exist between the purchase preferences of social network friends and those of\u0000the target user, reducing the influence of friends relative to the target\u0000user's own preferences. To address these challenges, this paper introduces the\u0000concept of ``Like-minded Peers'' (LMP), representing users whose preferences\u0000align with the target user's current session based on their historical\u0000sessions. This is the first work, to our knowledge, that uses LMP to enhance\u0000the modeling of social influence in SSR. This approach not only alleviates the\u0000problem of friend data sparsity but also effectively incorporates users with\u0000similar preferences to the target user. We propose a novel model named\u0000Transformer Encoder with Graph Attention Aggregator Recommendation (TEGAARec),\u0000which includes the TEGAA module and the GAT-based social aggregation module.\u0000The TEGAA module captures and merges both long-term and short-term interests\u0000for target users and LMP users. Concurrently, the GAT-based social aggregation\u0000module is designed to aggregate the target users' dynamic interests and social\u0000influence in a weighted manner. Extensive experiments on four real-world\u0000datasets demonstrate the efficacy and superiority of our proposed model and\u0000ablation studies are done to illustrate the contributions of each component in\u0000TEGAARec.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142227853","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

Detecting Calls to Action in Multimodal Content: Analysis of the 2021 German Federal Election Campaign on Instagram 检测多模态内容中的行动号召：分析 Instagram 上的 2021 年德国联邦大选活动

arXiv - CS - Social and Information Networks Pub Date : 2024-09-04 DOI: arxiv-2409.02690

Michael Achmann-Denkler, Jakob Fehle, Mario Haim, Christian Wolff

引用次数: 0

What is Normal? A Big Data Observational Science Model of Anonymized Internet Traffic 什么是正常？匿名互联网流量的大数据观察科学模型

arXiv - CS - Social and Information Networks Pub Date : 2024-09-04 DOI: arxiv-2409.03111

Jeremy Kepner, Hayden Jananthan, Michael Jones, William Arcand, David Bestor, William Bergeron, Daniel Burrill, Aydin Buluc, Chansup Byun, Timothy Davis, Vijay Gadepally, Daniel Grant, Michael Houle, Matthew Hubbell, Piotr Luszczek, Lauren Milechin, Chasen Milner, Guillermo Morales, Andrew Morris, Julie Mullen, Ritesh Patel, Alex Pentland, Sandeep Pisharody, Andrew Prout, Albert Reuther, Antonio Rosa, Gabriel Wachman, Charles Yee, Peter Michaleas

引用次数: 0

Do We Trust What They Say or What They Do? A Multimodal User Embedding Provides Personalized Explanations 我们相信他们说的话还是做的事？多模态用户嵌入提供个性化解释

arXiv - CS - Social and Information Networks Pub Date : 2024-09-04 DOI: arxiv-2409.02965

Zhicheng Ren, Zhiping Xiao, Yizhou Sun

{"title":"Do We Trust What They Say or What They Do? A Multimodal User Embedding Provides Personalized Explanations","authors":"Zhicheng Ren, Zhiping Xiao, Yizhou Sun","doi":"arxiv-2409.02965","DOIUrl":"https://doi.org/arxiv-2409.02965","url":null,"abstract":"With the rapid development of social media, the importance of analyzing\u0000social network user data has also been put on the agenda. User representation\u0000learning in social media is a critical area of research, based on which we can\u0000conduct personalized content delivery, or detect malicious actors. Being more\u0000complicated than many other types of data, social network user data has\u0000inherent multimodal nature. Various multimodal approaches have been proposed to\u0000harness both text (i.e. post content) and relation (i.e. inter-user\u0000interaction) information to learn user embeddings of higher quality. The advent\u0000of Graph Neural Network models enables more end-to-end integration of user text\u0000embeddings and user interaction graphs in social networks. However, most of\u0000those approaches do not adequately elucidate which aspects of the data - text\u0000or graph structure information - are more helpful for predicting each specific\u0000user under a particular task, putting some burden on personalized downstream\u0000analysis and untrustworthy information filtering. We propose a simple yet\u0000effective framework called Contribution-Aware Multimodal User Embedding (CAMUE)\u0000for social networks. We have demonstrated with empirical evidence, that our\u0000approach can provide personalized explainable predictions, automatically\u0000mitigating the impact of unreliable information. We also conducted case studies\u0000to show how reasonable our results are. We observe that for most users, graph\u0000structure information is more trustworthy than text information, but there are\u0000some reasonable cases where text helps more. Our work paves the way for more\u0000explainable, reliable, and effective social media user embedding which allows\u0000for better personalized content delivery.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142214722","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

FastEnsemble: A new scalable ensemble clustering method FastEnsemble：一种新的可扩展集合聚类方法

arXiv - CS - Social and Information Networks Pub Date : 2024-09-03 DOI: arxiv-2409.02077

Yasamin Tabatabaee, Eleanor Wedell, Minhyuk Park, Tandy Warnow

引用次数: 0

Preserving the Ephemeral: Instagram Story Archiving with the Tidal Tales Plugin 保存短暂：用潮汐故事插件存档 Instagram 故事

arXiv - CS - Social and Information Networks Pub Date : 2024-09-03 DOI: arxiv-2409.01880

Michael Achmann-Denkler, Christian Wolff

引用次数: 0

Fair Railway Network Design 公平铁路网设计

arXiv - CS - Social and Information Networks Pub Date : 2024-09-03 DOI: arxiv-2409.02152

Zixu He, Sirin Botan, Jérôme Lang, Abdallah Saffidine, Florian Sikora, Silas Workman

引用次数: 0

Wikipedia in Wartime: Experiences of Wikipedians Maintaining Articles About the Russia-Ukraine War 战时的维基百科：维基人维护俄乌战争相关文章的经验

arXiv - CS - Social and Information Networks Pub Date : 2024-09-03 DOI: arxiv-2409.02304

Laura Kurek, Ceren Budak, Eric Gilbert

{"title":"Wikipedia in Wartime: Experiences of Wikipedians Maintaining Articles About the Russia-Ukraine War","authors":"Laura Kurek, Ceren Budak, Eric Gilbert","doi":"arxiv-2409.02304","DOIUrl":"https://doi.org/arxiv-2409.02304","url":null,"abstract":"How do Wikipedians maintain an accurate encyclopedia during an ongoing\u0000geopolitical conflict where state actors might seek to spread disinformation or\u0000conduct an information operation? In the context of the Russia-Ukraine War,\u0000this question becomes more pressing, given the Russian government's extensive\u0000history of orchestrating information campaigns. We conducted an interview study\u0000with 13 expert Wikipedians involved in the Russo-Ukrainian War topic area on\u0000the English-language edition of Wikipedia. While our participants did not\u0000perceive there to be clear evidence of a state-backed information operation,\u0000they agreed that war-related articles experienced high levels of disruptive\u0000editing from both Russia-aligned and Ukraine-aligned accounts. The\u0000English-language edition of Wikipedia had existing policies and processes at\u0000its disposal to counter such disruption. State-backed or not, the disruptive\u0000activity created time-intensive maintenance work for our participants. Finally,\u0000participants considered English-language Wikipedia to be more resilient than\u0000social media in preventing the spread of false information online. We conclude\u0000by discussing sociotechnical implications for Wikipedia and social platforms.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142226909","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

A dataset of Open Source Intelligence (OSINT) Tweets about the Russo-Ukrainian war 有关俄乌战争的开放源代码情报 (OSINT) 推文数据集

arXiv - CS - Social and Information Networks Pub Date : 2024-09-02 DOI: arxiv-2409.01052

Johannes Niu, Mila Stillman, Philipp Seeberger, Anna Kruspe

引用次数: 0

Polaris: Sampling from the Multigraph Configuration Model with Prescribed Color Assortativity 北极星从多图谱配置模型中采样，规定颜色同类性

arXiv - CS - Social and Information Networks Pub Date : 2024-09-02 DOI: arxiv-2409.01363

Giulia Preti, Matteo Riondato, Aristides Gionis, Gianmarco De Francisci Morales

{"title":"Polaris: Sampling from the Multigraph Configuration Model with Prescribed Color Assortativity","authors":"Giulia Preti, Matteo Riondato, Aristides Gionis, Gianmarco De Francisci Morales","doi":"arxiv-2409.01363","DOIUrl":"https://doi.org/arxiv-2409.01363","url":null,"abstract":"We introduce Polaris, a network null model for colored multi-graphs that\u0000preserves the Joint Color Matrix. Polaris is specifically designed for studying\u0000network polarization, where vertices belong to a side in a debate or a partisan\u0000group, represented by a vertex color, and relations have different strengths,\u0000represented by an integer-valued edge multiplicity. The key feature of Polaris\u0000is preserving the Joint Color Matrix (JCM) of the multigraph, which specifies\u0000the number of edges connecting vertices of any two given colors. The JCM is the\u0000basic property that determines color assortativity, a fundamental aspect in\u0000studying homophily and segregation in polarized networks. By using Polaris,\u0000network scientists can test whether a phenomenon is entirely explained by the\u0000JCM of the observed network or whether other phenomena might be at play.\u0000Technically, our null model is an extension of the configuration model: an\u0000ensemble of colored multigraphs characterized by the same degree sequence and\u0000the same JCM. To sample from this ensemble, we develop a suite of Markov Chain\u0000Monte Carlo algorithms, collectively named Polaris-*. It includes Polaris-B, an\u0000adaptation of a generic Metropolis-Hastings algorithm, and Polaris-C, a faster,\u0000specialized algorithm with higher acceptance probabilities. This new null model\u0000and the associated algorithms provide a more nuanced toolset for examining\u0000polarization in social networks, thus enabling statistically sound conclusions.","PeriodicalId":501032,"journal":{"name":"arXiv - CS - Social and Information Networks","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142214729","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