Most of the existing deep-learning-based network analysis techniques focus on the problem of learning low-dimensional node representations. However, networks can also be seen in the light of edges interlinking pairs of nodes. The broad goal of this paper is to introduce a deep-learning framework focused on computing edge-centric network embeddings. We present a novel approach called ECNE, which instead of computing edge embeddings by aggregating node embeddings, computes them directly. ECNE leverages the notion of line graph of a graph coupled with an edge weighting mechanism to preserve the dynamic of the original graph in the line graph. We show that ECNE brings benefits wrt the state-of-the-art.
{"title":"Edge-centric network analysis","authors":"G. Pirrò","doi":"10.1145/3487351.3488329","DOIUrl":"https://doi.org/10.1145/3487351.3488329","url":null,"abstract":"Most of the existing deep-learning-based network analysis techniques focus on the problem of learning low-dimensional node representations. However, networks can also be seen in the light of edges interlinking pairs of nodes. The broad goal of this paper is to introduce a deep-learning framework focused on computing edge-centric network embeddings. We present a novel approach called ECNE, which instead of computing edge embeddings by aggregating node embeddings, computes them directly. ECNE leverages the notion of line graph of a graph coupled with an edge weighting mechanism to preserve the dynamic of the original graph in the line graph. We show that ECNE brings benefits wrt the state-of-the-art.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134377069","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}
COVID-19 pandemic has changed almost every aspect of people's lives around the world. Along with non-pharmaceutical interventions such as physical distancing, vaccination is one of the proposed solutions to control the spread of this pandemic. However, so much fake information is spread on social media websites about the vaccination. In this paper, we study the problem of fake news detection on Twitter network. After collecting a dataset and pre-processing, a set of features are extracted from the tweets. This includes the tweet's length and its keywords, number of followers, sentiment, and readability scores. In the next phase, six well-known classifiers are executed on this data, and the best result with the highest accuracy is chosen for the community detection process to study and track the evolution of fake news campaigns. For the analysis, we considered multiple criteria such as the number of communities, their sizes, leaders, and topics. The results of this research can help decision-makers to understand the underlying and formation of fake news campaigns.
{"title":"Fake news and COVID-19 vaccination: a comparative study","authors":"Farzaneh Jouyandeh, Sarvnaz Sadeghi, Bahareh Rahmatikargar, Pooya Moradian Zadeh","doi":"10.1145/3487351.3490960","DOIUrl":"https://doi.org/10.1145/3487351.3490960","url":null,"abstract":"COVID-19 pandemic has changed almost every aspect of people's lives around the world. Along with non-pharmaceutical interventions such as physical distancing, vaccination is one of the proposed solutions to control the spread of this pandemic. However, so much fake information is spread on social media websites about the vaccination. In this paper, we study the problem of fake news detection on Twitter network. After collecting a dataset and pre-processing, a set of features are extracted from the tweets. This includes the tweet's length and its keywords, number of followers, sentiment, and readability scores. In the next phase, six well-known classifiers are executed on this data, and the best result with the highest accuracy is chosen for the community detection process to study and track the evolution of fake news campaigns. For the analysis, we considered multiple criteria such as the number of communities, their sizes, leaders, and topics. The results of this research can help decision-makers to understand the underlying and formation of fake news campaigns.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124469601","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}
Given a domain-specific set of concept labels, taxonomy induction is the problem of inducing a taxonomy over the concept labels. Despite its importance in problems such as e-commerce, and some algorithmic research as a consequence, practical tools for taxonomy induction and interactive visualization do not currently exist. To be truly useful, such a tool must permit a reasonable solution in a relatively unsupervised setting, and be applicable to general subsets of concept labels. In this paper, we present an unsupervised, end-to-end taxonomy induction system for arbitrary concept-labels from the e-commerce domain. Our system only takes a simple text file as input and yields a tree-like taxonomy that can be rendered on a browser, and that a non-technical user can interact with. Important components of the system can also be customized by a technically experienced user.
{"title":"Unsupervised real-time induction and interactive visualization of taxonomies over domain-specific concepts","authors":"M. Kejriwal, Ke Shen","doi":"10.1145/3487351.3489481","DOIUrl":"https://doi.org/10.1145/3487351.3489481","url":null,"abstract":"Given a domain-specific set of concept labels, taxonomy induction is the problem of inducing a taxonomy over the concept labels. Despite its importance in problems such as e-commerce, and some algorithmic research as a consequence, practical tools for taxonomy induction and interactive visualization do not currently exist. To be truly useful, such a tool must permit a reasonable solution in a relatively unsupervised setting, and be applicable to general subsets of concept labels. In this paper, we present an unsupervised, end-to-end taxonomy induction system for arbitrary concept-labels from the e-commerce domain. Our system only takes a simple text file as input and yields a tree-like taxonomy that can be rendered on a browser, and that a non-technical user can interact with. Important components of the system can also be customized by a technically experienced user.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127815914","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}
Yang Zhang, Ruohan Zong, Lanyu Shang, Ziyi Kou, Dong Wang
Social sensing has emerged as a pervasive and scalable sensing paradigm to obtain timely information of the physical world from "human sensors". In this paper, we study a new extremely-sparse disaster damage assessment (DBA) problem in social sensing. The objective is to automatically assess the damage severity of affected areas in a disaster event by leveraging the imagery data reported on online social media with extremely sparse training data (e.g., only 1% of the data samples have labels). Our problem is motivated by the limitation of current DDA solutions that often require a significant amount of high-quality training data to learn an effective DDA model. We identify two critical challenges in solving our problem: i) it remains to be a fundamental challenge on how to effectively train a reliable DDA model given the lack of sufficient damage severity labels; ii) it is a difficult task to capture the excessive and fine-grained damage-related features in each image for accurate damage assessment. In this paper, we propose ContrastDDA, a deep contrastive learning approach to address the extremely-sparse DDA problem by designing an integrated contrastive and augmentative neural network architecture for accurate disaster damage assessment using the extremely sparse training samples. The evaluation results on two real-world DDA applications demonstrate that ContrastDDA clearly outperforms state-of-the-art deep learning and semi-supervised learning baselines with the highest DDA accuracy under different application scenarios.
{"title":"A deep contrastive learning approach to extremely-sparse disaster damage assessment in social sensing","authors":"Yang Zhang, Ruohan Zong, Lanyu Shang, Ziyi Kou, Dong Wang","doi":"10.1145/3487351.3488318","DOIUrl":"https://doi.org/10.1145/3487351.3488318","url":null,"abstract":"Social sensing has emerged as a pervasive and scalable sensing paradigm to obtain timely information of the physical world from \"human sensors\". In this paper, we study a new extremely-sparse disaster damage assessment (DBA) problem in social sensing. The objective is to automatically assess the damage severity of affected areas in a disaster event by leveraging the imagery data reported on online social media with extremely sparse training data (e.g., only 1% of the data samples have labels). Our problem is motivated by the limitation of current DDA solutions that often require a significant amount of high-quality training data to learn an effective DDA model. We identify two critical challenges in solving our problem: i) it remains to be a fundamental challenge on how to effectively train a reliable DDA model given the lack of sufficient damage severity labels; ii) it is a difficult task to capture the excessive and fine-grained damage-related features in each image for accurate damage assessment. In this paper, we propose ContrastDDA, a deep contrastive learning approach to address the extremely-sparse DDA problem by designing an integrated contrastive and augmentative neural network architecture for accurate disaster damage assessment using the extremely sparse training samples. The evaluation results on two real-world DDA applications demonstrate that ContrastDDA clearly outperforms state-of-the-art deep learning and semi-supervised learning baselines with the highest DDA accuracy under different application scenarios.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"9 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116655764","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}
P. Morales, Jean-Philippe Cointet, Gabriel Muñoz Zolotoochin
Traditionally, public opinion on different issues of public debate has been studied through polls and surveys. Recent advancements in network ideological scaling methods, however, have shown that digital behavioral traces in social media platforms can be used to mine opinions at a massive scale. This has yet to be shown to work beyond one-dimensional opinion scales, which are best suited for two-party systems and binary social divides such as those observed in the US. In this article, we use multidimensional ideological scaling for coupled with referential attitudinal data for some nodes. We show that opinions can be mined in a multitude of issues: from social networks, embedding them in ideological spaces where dimensions stand for indicators of positive and negative opinions, towards issues of public debate. This method does not require text analysis and is thus language independent. We illustrate this approach on the Twitter follower network of French users leveraging political survey data.
{"title":"Unfolding the dimensionality structure of social networks in ideological embeddings","authors":"P. Morales, Jean-Philippe Cointet, Gabriel Muñoz Zolotoochin","doi":"10.1145/3487351.3489441","DOIUrl":"https://doi.org/10.1145/3487351.3489441","url":null,"abstract":"Traditionally, public opinion on different issues of public debate has been studied through polls and surveys. Recent advancements in network ideological scaling methods, however, have shown that digital behavioral traces in social media platforms can be used to mine opinions at a massive scale. This has yet to be shown to work beyond one-dimensional opinion scales, which are best suited for two-party systems and binary social divides such as those observed in the US. In this article, we use multidimensional ideological scaling for coupled with referential attitudinal data for some nodes. We show that opinions can be mined in a multitude of issues: from social networks, embedding them in ideological spaces where dimensions stand for indicators of positive and negative opinions, towards issues of public debate. This method does not require text analysis and is thus language independent. We illustrate this approach on the Twitter follower network of French users leveraging political survey data.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126886028","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}
Risul Islam, Ben Treves, Md Omar Faruk Rokon, M. Faloutsos
How can we detect and analyze hyperlink-driven misbehavior in online forums? Online forums contain enormous amounts of user-generated content, with threads and comments frequently supplemented by hyperlinks. These hyperlinks are often posted with malicious intention and we refer to this as 'hyperlink-driven misbehavior'. We present LinkMan, a systematic suite of capabilities, to detect and analyze hyperlink-driven misbehavior in online forums. We take a unique perspective focusing on hyperlink sharing practices of the users to spot misbehavior. LinkMan can categorize these hyperlinks as: a) phishing, b) spamming, and b) promoting malicious products. Our approach consists of three high-level phases: (a) extracting hyperlinks from the textual data, (b) identifying misbehaving hyperlinks, and (c) modeling the behavioral patterns of hyperlink sharing, where we identify key hyperlinks and analyze the collaboration dynamics of hyperlink sharing. In addition, we implement our approach as a powerful and easy-to-use open platform for practitioners. We apply LinkMan to spot misbehavior from three online security forums, where we expect the users to be more security-aware. We show that our approach works very well in terms of retrieving and classifying hyperlinks compared to previous solutions. Furthermore, we find non-trivial and often systematic misbehavior: (a) we find a total of 637 misbehaving hyperlinks, and (b) we identify 30 colluding groups of users in terms of promoting hyperlinks. Our work is a significant step towards mining online forums and detecting misbehaving users comprehensively.
{"title":"LinkMan: hyperlink-driven misbehavior detection in online security forums","authors":"Risul Islam, Ben Treves, Md Omar Faruk Rokon, M. Faloutsos","doi":"10.1145/3487351.3488323","DOIUrl":"https://doi.org/10.1145/3487351.3488323","url":null,"abstract":"How can we detect and analyze hyperlink-driven misbehavior in online forums? Online forums contain enormous amounts of user-generated content, with threads and comments frequently supplemented by hyperlinks. These hyperlinks are often posted with malicious intention and we refer to this as 'hyperlink-driven misbehavior'. We present LinkMan, a systematic suite of capabilities, to detect and analyze hyperlink-driven misbehavior in online forums. We take a unique perspective focusing on hyperlink sharing practices of the users to spot misbehavior. LinkMan can categorize these hyperlinks as: a) phishing, b) spamming, and b) promoting malicious products. Our approach consists of three high-level phases: (a) extracting hyperlinks from the textual data, (b) identifying misbehaving hyperlinks, and (c) modeling the behavioral patterns of hyperlink sharing, where we identify key hyperlinks and analyze the collaboration dynamics of hyperlink sharing. In addition, we implement our approach as a powerful and easy-to-use open platform for practitioners. We apply LinkMan to spot misbehavior from three online security forums, where we expect the users to be more security-aware. We show that our approach works very well in terms of retrieving and classifying hyperlinks compared to previous solutions. Furthermore, we find non-trivial and often systematic misbehavior: (a) we find a total of 637 misbehaving hyperlinks, and (b) we identify 30 colluding groups of users in terms of promoting hyperlinks. Our work is a significant step towards mining online forums and detecting misbehaving users comprehensively.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127025268","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}
Berk Kardaş, İsmail Erdem Bayar, Tansel Özyer, R. Alhajj
Nowadays, with the rapid increase in popularity of online social networks (OSNs), these platforms are realized as ideal places for spammers. Unfortunately, these spammers can easily publish malicious content, advertise phishing scams by taking advantage of OSNs. Therefore, effective identification and filtering of spam tweets will be beneficial to both OSNs and users. However, it is becoming increasingly difficult to check and eliminate spam tweets due to this great flow of posts. Motivated by these observations, in this paper we propose an approach for the detection of spam tweets using machine learning and effective preprocessing techniques. The approach proposes the advantages of the preprocessing and which of these preprocessing techniques are the most effective. To compare these techniques UtkML Twitter spam dataset is used in testing. After the most effective methods determined, the detection accuracy of the spam tweets will be better optimized by combining them. We have evaluated our solution with four different machine learning algorithms namely - Naïve Bayes Classifier, Neural Network, Logistic Regression and Support Vector Machine. With SVM Classifier, we are able to achieve an accuracy of 93.02%. Experimental results show that our approach can improve the performance of spam tweet classification effectively.
{"title":"Detecting spam tweets using machine learning and effective preprocessing","authors":"Berk Kardaş, İsmail Erdem Bayar, Tansel Özyer, R. Alhajj","doi":"10.1145/3487351.3490968","DOIUrl":"https://doi.org/10.1145/3487351.3490968","url":null,"abstract":"Nowadays, with the rapid increase in popularity of online social networks (OSNs), these platforms are realized as ideal places for spammers. Unfortunately, these spammers can easily publish malicious content, advertise phishing scams by taking advantage of OSNs. Therefore, effective identification and filtering of spam tweets will be beneficial to both OSNs and users. However, it is becoming increasingly difficult to check and eliminate spam tweets due to this great flow of posts. Motivated by these observations, in this paper we propose an approach for the detection of spam tweets using machine learning and effective preprocessing techniques. The approach proposes the advantages of the preprocessing and which of these preprocessing techniques are the most effective. To compare these techniques UtkML Twitter spam dataset is used in testing. After the most effective methods determined, the detection accuracy of the spam tweets will be better optimized by combining them. We have evaluated our solution with four different machine learning algorithms namely - Naïve Bayes Classifier, Neural Network, Logistic Regression and Support Vector Machine. With SVM Classifier, we are able to achieve an accuracy of 93.02%. Experimental results show that our approach can improve the performance of spam tweet classification effectively.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129195577","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}
Kin Wai Ng, Sameera Horawalavithana, Adriana Iamnitchi
Modeling social media activity has numerous practical implications such as designing and testing intervention techniques to mitigate disinformation or delivering critical information during disaster relief operations. In this paper we propose a modeling technique that forecasts topic-specific daily volume of social media activities by using both exogenous signals, such as news or armed conflicts records, and endogenous data from the social media platform we model. Empirical evaluations with real datasets from Twitter on two different contexts each composed of multiple interrelated topics demonstrate the effectiveness of our solution.
{"title":"Forecasting topic activity with exogenous and endogenous information signals in Twitter","authors":"Kin Wai Ng, Sameera Horawalavithana, Adriana Iamnitchi","doi":"10.1145/3487351.3488344","DOIUrl":"https://doi.org/10.1145/3487351.3488344","url":null,"abstract":"Modeling social media activity has numerous practical implications such as designing and testing intervention techniques to mitigate disinformation or delivering critical information during disaster relief operations. In this paper we propose a modeling technique that forecasts topic-specific daily volume of social media activities by using both exogenous signals, such as news or armed conflicts records, and endogenous data from the social media platform we model. Empirical evaluations with real datasets from Twitter on two different contexts each composed of multiple interrelated topics demonstrate the effectiveness of our solution.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129218987","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}
L. Vassio, M. Garetto, C. Chiasserini, Emilio Leonardi
A relevant fraction of human interactions occurs on online social networks. Freshness of content seems to play an important role, with content popularity rapidly vanishing over time. In this paper, we investigate how influencers' generated content (i.e., posts) attracts interactions, measured by number of likes or reactions. We analyse the activity of Italian influencers and followers over more than 5 years, focusing on two popular social networks: Facebook and Instagram, including more than 13 billion interactions and about 4 million posts. We characterise the influencers' and followers' behaviour over time, show that influencers' posts are short-lived with an exponential temporal decay, and characterise the time evolution of the interactions from their initial peak till the end of a post lifetime. Finally, leveraging our findings, we discuss how they can be exploited to develop an analytical model of the interactions temporal dynamics.
{"title":"Temporal dynamics of posts and user engagement of influencers on Facebook and Instagram","authors":"L. Vassio, M. Garetto, C. Chiasserini, Emilio Leonardi","doi":"10.1145/3487351.3488340","DOIUrl":"https://doi.org/10.1145/3487351.3488340","url":null,"abstract":"A relevant fraction of human interactions occurs on online social networks. Freshness of content seems to play an important role, with content popularity rapidly vanishing over time. In this paper, we investigate how influencers' generated content (i.e., posts) attracts interactions, measured by number of likes or reactions. We analyse the activity of Italian influencers and followers over more than 5 years, focusing on two popular social networks: Facebook and Instagram, including more than 13 billion interactions and about 4 million posts. We characterise the influencers' and followers' behaviour over time, show that influencers' posts are short-lived with an exponential temporal decay, and characterise the time evolution of the interactions from their initial peak till the end of a post lifetime. Finally, leveraging our findings, we discuss how they can be exploited to develop an analytical model of the interactions temporal dynamics.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"18 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114930309","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}
Yichen Wang, Richard O. Han, Tamara Lehman, Q. Lv, Shivakant Mishra
Social media platforms have been exploited to disseminate misinformation in recent years. The widespread online misinformation has been shown to affect users' beliefs and is connected to social impact such as polarization. In this work, we focus on misinformation's impact on specific user behavior and aim to understand whether general Twitter users changed their behavior after being exposed to misinformation. We compare the before and after behavior of exposed users to determine whether the frequency of the tweets they posted, or the sentiment of their tweets underwent any significant change. Our results indicate that users overall exhibited statistically significant changes in behavior across some of these metrics. Through language distance analysis, we show that exposed users were already different from baseline users before the exposure. We also study the characteristics of two specific user groups, multi-exposure and extreme change groups, which were potentially highly impacted. Finally, we study if the changes in the behavior of the users after exposure to misinformation tweets vary based on the number of their followers or the number of followers of the tweet authors, and find that their behavioral changes are all similar.
{"title":"Analyzing behavioral changes of Twitter users after exposure to misinformation","authors":"Yichen Wang, Richard O. Han, Tamara Lehman, Q. Lv, Shivakant Mishra","doi":"10.1145/3487351.3492718","DOIUrl":"https://doi.org/10.1145/3487351.3492718","url":null,"abstract":"Social media platforms have been exploited to disseminate misinformation in recent years. The widespread online misinformation has been shown to affect users' beliefs and is connected to social impact such as polarization. In this work, we focus on misinformation's impact on specific user behavior and aim to understand whether general Twitter users changed their behavior after being exposed to misinformation. We compare the before and after behavior of exposed users to determine whether the frequency of the tweets they posted, or the sentiment of their tweets underwent any significant change. Our results indicate that users overall exhibited statistically significant changes in behavior across some of these metrics. Through language distance analysis, we show that exposed users were already different from baseline users before the exposure. We also study the characteristics of two specific user groups, multi-exposure and extreme change groups, which were potentially highly impacted. Finally, we study if the changes in the behavior of the users after exposure to misinformation tweets vary based on the number of their followers or the number of followers of the tweet authors, and find that their behavioral changes are all similar.","PeriodicalId":320904,"journal":{"name":"Proceedings of the 2021 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129193176","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：