Abstract:Online social media enables mass-level, transparent, and democratized discussion on numerous socio-political issues. Due to such openness, these platforms often endure manipulation and misinformation -leading to negative impacts. To prevent such harmful activities, platform moderators employ countermeasures to safeguard against actors violating their rules. However, the correlation between publicly outlined policies and employed action is less clear to general people. In this work, we examine violations and su… Show more
“…One possible explanation could be that the massive audience engaging in online conversations around the conflict consequently lured in a larger amount of malicious activity compared to the French election. These findings confirm previous work which showed peaks of suspensions [ 26 , 43 ] and a larger number of new accounts among those suspended [ 26 , 28 , 44 ].…”
Section: Resultssupporting
confidence: 92%
“…17 . We find similar results in both datasets: suspended users shared a larger amount of Harmful and Spam messages compared to active users; New Suspended users were particularly active in spamming campaigns in both datasets, and these findings are in line with previous work [ 27 , 43 , 44 ]. Figure 17 Proportion of tweets that were labeled as Harmful, Normal or Spam for each class of accounts for UK-RU (left) and FR-22 (right) …”
Section: Resultssupporting
confidence: 90%
“…Following a similar approach, Chowdhury et al [ 43 ] identify over 2M suspended accounts that engage mostly in political and marketing campaigns, showing that over 60% of them were active for more than two years on Twitter before being suspended. In follow-up work, the same authors [ 44 ] aim to identify factors that lead to suspension during the 2020 US Presidential election, showing that suspended users use more curse and derogatory words, and tend to share more right-leaning news.…”
Social media moderation policies are often at the center of public debate, and their implementation and enactment are sometimes surrounded by a veil of mystery. Unsurprisingly, due to limited platform transparency and data access, relatively little research has been devoted to characterizing moderation dynamics, especially in the context of controversial events and the platform activity associated with them. Here, we study the dynamics of account creation and suspension on Twitter during two global political events: Russia’s invasion of Ukraine and the 2022 French Presidential election. Leveraging a large-scale dataset of 270M tweets shared by 16M users in multiple languages over several months, we identify peaks of suspicious account creation and suspension, and we characterize behaviors that more frequently lead to account suspension. We show how large numbers of accounts get suspended within days of their creation. Suspended accounts tend to mostly interact with legitimate users, as opposed to other suspicious accounts, making unwarranted and excessive use of reply and mention features, and sharing large amounts of spam and harmful content. While we are only able to speculate about the specific causes leading to a given account suspension, our findings contribute to shedding light on patterns of platform abuse and subsequent moderation during major events.
“…One possible explanation could be that the massive audience engaging in online conversations around the conflict consequently lured in a larger amount of malicious activity compared to the French election. These findings confirm previous work which showed peaks of suspensions [ 26 , 43 ] and a larger number of new accounts among those suspended [ 26 , 28 , 44 ].…”
Section: Resultssupporting
confidence: 92%
“…17 . We find similar results in both datasets: suspended users shared a larger amount of Harmful and Spam messages compared to active users; New Suspended users were particularly active in spamming campaigns in both datasets, and these findings are in line with previous work [ 27 , 43 , 44 ]. Figure 17 Proportion of tweets that were labeled as Harmful, Normal or Spam for each class of accounts for UK-RU (left) and FR-22 (right) …”
Section: Resultssupporting
confidence: 90%
“…Following a similar approach, Chowdhury et al [ 43 ] identify over 2M suspended accounts that engage mostly in political and marketing campaigns, showing that over 60% of them were active for more than two years on Twitter before being suspended. In follow-up work, the same authors [ 44 ] aim to identify factors that lead to suspension during the 2020 US Presidential election, showing that suspended users use more curse and derogatory words, and tend to share more right-leaning news.…”
Social media moderation policies are often at the center of public debate, and their implementation and enactment are sometimes surrounded by a veil of mystery. Unsurprisingly, due to limited platform transparency and data access, relatively little research has been devoted to characterizing moderation dynamics, especially in the context of controversial events and the platform activity associated with them. Here, we study the dynamics of account creation and suspension on Twitter during two global political events: Russia’s invasion of Ukraine and the 2022 French Presidential election. Leveraging a large-scale dataset of 270M tweets shared by 16M users in multiple languages over several months, we identify peaks of suspicious account creation and suspension, and we characterize behaviors that more frequently lead to account suspension. We show how large numbers of accounts get suspended within days of their creation. Suspended accounts tend to mostly interact with legitimate users, as opposed to other suspicious accounts, making unwarranted and excessive use of reply and mention features, and sharing large amounts of spam and harmful content. While we are only able to speculate about the specific causes leading to a given account suspension, our findings contribute to shedding light on patterns of platform abuse and subsequent moderation during major events.
“…Centralized approaches to misinformation detection include using machine learning models for classifying whether content is accurate [13,20,85,103], and leveraging human moderators and third party fact-checking and news organizations [7,10]. Centralized approaches to dealing with misinformation include displaying warning labels next to, downranking, reduction (e.g., shadow-banning), or removal of the content or suspension of offender accounts [18,24,27,38,75,77,84].…”
Figure 1: Upon visiting a webpage, the Trustnet extension opens a pane on the side showing the assessments of the page by those the user follows or trusts. The figure shows a news article (left) and a Youtube video (right) assessed by users of the study.
“…Authors in (Majó-Vázquez et al 2021) examine the role of suspended accounts in political discussions during the 2017 elections in France, the UK, and Germany, while they show that these accounts were more likely to be associated with political extremism and misinformation. Similarly, in (Chowdhury et al 2021) they examine the factors contributing to the suspension mechanism following the 2020 US presidential election by identifying several factors, including the use of certain keywords, the presence of bots, and the posting of misinformation.…”
Twitter as one of the most popular social networks, offers a means for communication and online discourse, which unfortunately has been the target of bots and fake accounts, leading to the manipulation and spreading of false information. Towards this end, we gather a challenging, multilingual dataset of social discourse on Twitter, originating from 9M users regarding the recent Russo-Ukrainian war, in order to detect the bot accounts and the conversation involving them. We collect the ground truth for our dataset through the Twitter API suspended accounts collection, containing approximately 343K of bot accounts and 8M of normal users. Additionally, we use a dataset provided by Botometer-V3 with 1,777 Varol, 483 German accounts, and 1,321 US accounts. Besides the publicly available datasets, we also manage to collect 2 independent datasets around popular discussion topics of the 2022 energy crisis and the 2022 conspiracy discussions. Both of the datasets were labeled according to the Twitter suspension mechanism. We build a novel ML model for bot detection using the state-of-the-art XGBoost model. We combine the model with a high volume of labeled tweets according to the Twitter suspension mechanism ground truth. This requires a limited set of profile features allowing labeling of the dataset in different time periods from the collection, as it is independent of the Twitter API. In comparison with Botometer our methodology achieves an average 11% higher ROC-AUC score over two real-case scenario datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
