Proceedings of the 14th ACM Web Science Conference 2022最新文献_第2页

Multimodal Zero-Shot Hateful Meme Detection 多模态零射击仇恨模因检测

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531557

Jiawen Zhu, R. Lee, Wen-Haw Chong

引用次数: 6

How to Conduct an Ethics Assessment of AI in Policing 如何对警务人工智能进行道德评估

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3539509

Zachary J. Goldberg

引用次数: 1

GNoM: Graph Neural Network Enhanced Language Models for Disaster Related Multilingual Text Classification 用于灾害相关多语言文本分类的图神经网络增强语言模型

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531561

Samujjwal Ghosh, Subhadeep Maji, M. Desarkar

{"title":"GNoM: Graph Neural Network Enhanced Language Models for Disaster Related Multilingual Text Classification","authors":"Samujjwal Ghosh, Subhadeep Maji, M. Desarkar","doi":"10.1145/3501247.3531561","DOIUrl":"https://doi.org/10.1145/3501247.3531561","url":null,"abstract":"Online social media works as a source of various valuable and actionable information during disasters. These information might be available in multiple languages due to the nature of user generated content. An effective system to automatically identify and categorize these actionable information should be capable to handle multiple languages and under limited supervision. However, existing works mostly focus on English language only with the assumption that sufficient labeled data is available. To overcome these challenges, we propose a multilingual disaster related text classification system which is capable to work undervmonolingual, cross-lingual and multilingual lingual scenarios and under limited supervision. Our end-to-end trainable framework combines the versatility of graph neural networks, by applying over the corpus, with the power of transformer based large language models, over examples, with the help of cross-attention between the two. We evaluate our framework over total nine English, Non-English and monolingual datasets invmonolingual, cross-lingual and multilingual lingual classification scenarios. Our framework outperforms state-of-the-art models in disaster domain and multilingual BERT baseline in terms of Weighted F1 score. We also show the generalizability of the proposed model under limited supervision.","PeriodicalId":136381,"journal":{"name":"Proceedings of the 14th ACM Web Science Conference 2022","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123811104","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: 2

Removal of Anti-Vaccine Content Impacts Social Media Discourse 删除反疫苗内容会影响社交媒体话语

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531548

Tamar Mitts, N. Pisharody, Jacob N. Shapiro

{"title":"Removal of Anti-Vaccine Content Impacts Social Media Discourse","authors":"Tamar Mitts, N. Pisharody, Jacob N. Shapiro","doi":"10.1145/3501247.3531548","DOIUrl":"https://doi.org/10.1145/3501247.3531548","url":null,"abstract":"Over the past several years, a growing number of social media platforms have begun taking an active role in content moderation and online speech regulation. While enforcement actions have been shown to improve outcomes within moderating platforms, less is known about possible spillover effects across platforms. We study the impact of removing groups promoting anti-vaccine content on Facebook on engagement with similar content on Twitter. We followed 160 Facebook groups discussing COVID-19 vaccines and prospectively tracked their removal from the platform between April and September 2021. We then identified users who cited these groups on Twitter, and examined their online behavior over time. Our findings from a stacked difference-in-differences analysis shows that users citing removed Facebook groups promoted more anti-vaccine content on Twitter in the month after the removals. In particular, users citing the removed groups used 10-33% more anti-vaccine keywords on Twitter, when compared to accounts citing groups that were not removed. Our results suggest that taking down anti-vaccine content on one platform can result in increased production of similar content on other platforms, raising questions about the overall effectiveness of these measures.","PeriodicalId":136381,"journal":{"name":"Proceedings of the 14th ACM Web Science Conference 2022","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127289815","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: 4

Socio-Economic Diversity in Human Annotations 人类注释的社会经济多样性

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531588

Shaoyang Fan, Pinar Barlas, Evgenia Christoforou, Jahna Otterbacher, S. Sadiq, Gianluca Demartini

{"title":"Socio-Economic Diversity in Human Annotations","authors":"Shaoyang Fan, Pinar Barlas, Evgenia Christoforou, Jahna Otterbacher, S. Sadiq, Gianluca Demartini","doi":"10.1145/3501247.3531588","DOIUrl":"https://doi.org/10.1145/3501247.3531588","url":null,"abstract":"Human annotations can help indexing digital resources as well as improving search and recommendation systems. Human annotators may carry their bias and stereotypes in the labels they create when annotating digital content. These are then reflected in machine learning models trained with such data. The result is a reinforcement loop where end-users are pushed stereotypical content by the search and recommendation systems they use on a daily basis. In order to break the loop, the impact on models of using diverse data that can better represent a diverse population has been looked at. In this work, we look at how human annotators in the US annotate digital content different from content which is popular on the Web and social media. We present the results of a controlled user study in which participants are asked to annotate videos of common tasks performed by people from various socio-economic backgrounds around the world. We test for the presence of social stereotypes and investigate the diversity of the provided annotations, especially since some abstract labels may reveal information about annotators’ emotional state and judgment. We observe different types of annotations for content from different socio-economic levels. Furthermore, we find regional and income level biases in annotation sentiment.","PeriodicalId":136381,"journal":{"name":"Proceedings of the 14th ACM Web Science Conference 2022","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122341871","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: 2

Auditing Search Query Suggestion Bias Through Recursive Algorithm Interrogation 通过递归算法查询审计搜索查询建议偏差

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531567

Fabian Haak, Philipp Schaer

引用次数: 2

Fork-based user migration in Blockchain Online Social Media 区块链在线社交媒体中基于分叉的用户迁移

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531597

Cheick Tidiane Ba, Andrea Michienzi, Barbara Guidi, Matteo Zignani, L. Ricci, S. Gaito

{"title":"Fork-based user migration in Blockchain Online Social Media","authors":"Cheick Tidiane Ba, Andrea Michienzi, Barbara Guidi, Matteo Zignani, L. Ricci, S. Gaito","doi":"10.1145/3501247.3531597","DOIUrl":"https://doi.org/10.1145/3501247.3531597","url":null,"abstract":"Nowadays, Online Social Media (OSM) are among the most popular web services. Traditional OSM are known to be affected by serious issues including misinformation, fake news, censorship, and privacy violations, to the point that a pressing demand for new paradigms is raised by users all over the world. Among such paradigms, the concepts around the Web 3.0 are fueling a new revolution of online sociality, pushing towards the adoption of innovative and groundbreaking technologies. In particular, the decentralization of social services through the blockchain technology is representing the most valid alternative to current OSM, enabling the development of rewarding strategies for value redistribution, and fake news detection. However, the so-called Blockchain Online Social Media (BOSMs) are far from being mature, with different platforms that continually try to redefine their services in order to attract larger audiences, thus causing blockchain forks and massive user migrations, with the latter dominating the dynamics of the current OSM landscape, too. In this paper, we deal with the evolution of BOSMs from the perspective of user migration across platforms as a consequence of a fork event. We propose a general user migration model applicable to BOSMs to represent the evolution patterns of fork-based migrations, the multi-interaction structural complexity of BOSMs, and their growth characteristics. Within this framework, we also cope with the task of predicting how users will behave in the case of a fork, i.e. they will remain on the original blockchain or they will migrate to the new one. We apply our framework to the case study of the Steem-Hive fork event, and show the importance of considering both social and economic information, regardless of the learning algorithm considered. To the best of our knowledge, this is the first study on blockchain fork and its related user migration.","PeriodicalId":136381,"journal":{"name":"Proceedings of the 14th ACM Web Science Conference 2022","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134314377","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: 11

Engineering Blockchain Enabling Win A Fortune Game among Novice through eAOM 工程区块链使新手通过eAOM赢得财富游戏

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3539018

Michellelibin Ten, WaiShiang Cheah, Y. Sim

引用次数: 0

Are Mutated Misinformation More Contagious? A Case Study of COVID-19 Misinformation on Twitter 变异的错误信息更具传染性吗?以推特上的新冠肺炎错误信息为例

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531562

Muheng Yan, Yu-Ru Lin, Wen-Ting Chung

{"title":"Are Mutated Misinformation More Contagious? A Case Study of COVID-19 Misinformation on Twitter","authors":"Muheng Yan, Yu-Ru Lin, Wen-Ting Chung","doi":"10.1145/3501247.3531562","DOIUrl":"https://doi.org/10.1145/3501247.3531562","url":null,"abstract":"The spread of online misinformation has become a major global risk. Understanding how misinformation propagates on social media is vital. While prior studies suggest that the content factors, such as emotion and topic in texts, are closely related to the dissemination of misinformation, the effect of users’ commentary on misinformation during its spreading on social media has been long overlooked. In this paper, we identify the patterns of “misinformation mutation” which captures ways misinformation is commented and shared by social media users. Our study focus on misinformation originated from digital news outlets and shared on Twitter. Through an analysis of over 240 thousand tweets capturing how users share COVID-19 pandemic-related misinformation news over a five-month period, we study the prevalence and factors of the misinformation mutation. We examine the different kinds of mutation in terms of how the article was cited from the news source, and how the content was edited, compared with its original text, and test the relationship between misinformation’s mutation and its spread on Twitter. Our results indicate a positive relationship between information mutation and spreading outcome – and such a relationship is stronger for news articles shared from non-credible outlets than those from credible ones. This study provides the first quantitative evidence of how misinformation propagation may be exacerbated by users’ commentary. Our study contributes to the understanding of misinformation spreading on social media and has implications for countering misinformation.","PeriodicalId":136381,"journal":{"name":"Proceedings of the 14th ACM Web Science Conference 2022","volume":"620 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134482609","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: 3

Narrative Building in Propaganda Networks on Indian Twitter 印度推特宣传网络的叙事构建

Proceedings of the 14th ACM Web Science Conference 2022 Pub Date : 2022-06-26 DOI: 10.1145/3501247.3531581

Saloni Dash, Arshia Arya, Sukhnidh Kaur, J. Pal

引用次数: 0