A Large-Scale Longitudinal Multimodal Dataset of State-Backed Information Operations on Twitter

Guo, Xiaobo; Vosoughi, Soroush

doi:10.1609/icwsm.v16i1.19375

Cited by 5 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, we collected all tweets that included at least one of such hashtags that were published during our 4 months observation window by non-banned users. We chose to rely on hashtags, which are the most widely used method of performing content-based Twitter data collection and filtering [4], [60]. Based on the ranked lists of each IO's top hashtags, our data collection step stops upon collecting data about a few hundreds of thousands of genuine users [9], [43].…”

Section: B Genuine Usersmentioning

confidence: 99%

Coordinated Behavior in Information Operations on Twitter

Cima,

Mannocci,

Avvenuti

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Online information operations (IOs) refer to organized attempts to tamper with the regular flow of information and to influence public opinion. Coordinated online behavior is a tactic frequently used by IO perpetrators to boost the spread and outreach of their messages. However, the exploitation of coordinated behavior within large-scale IOs is still largely unexplored. Here, we build a novel dataset comprising around 624K users and 4M tweets to study how online coordination was used in two recent IOs carried out on Twitter. We investigate the interplay between coordinated behavior and IOs with state-of-the-art network science and coordination detection methods, providing evidence that the perpetrators of both IOs were indeed strongly coordinated. Furthermore, we propose quantitative indicators and analyses to study the different patterns of coordination, uncovering a malicious group of users that managed to hold a central position in the discussion network, and others who remained at the periphery of the network, with limited interactions with genuine users. The nuanced results enabled by our analysis provide insights into the strategies, development, and effectiveness of the IOs. Overall, our results demonstrate that the analysis of coordinated behavior in IOs can contribute to safeguarding the integrity of online platforms.

show abstract

Section: B Genuine Usersmentioning

confidence: 99%

Coordinated Behavior in Information Operations on Twitter

Cima,

Mannocci,

Avvenuti

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The dataset is used for building a series of classification models from which SVM showed the best performance (F1-score is 93.32%). Moreover, Guo & Vosoughi (2022) build a large-scale dataset that contains sub-datasets with tweets and accounts affiliated with 14 countries spanning more than 3 years useful for tasks like analyzing state-sponsored propaganda.…”

Section: Background and Related Researchmentioning

confidence: 99%

Design Lessons from Building Deep Learning Disinformation Generation and Detection Solutions

Maathuis

Kerkhof

Godschalk

et al. 2023

eccws

View full text Add to dashboard Cite

In its essence, social media is on its way of representing the superposition of all digital representations of human concepts, ideas, believes, attitudes, and experiences. In this realm, the information is not only shared, but also {mis, dis}interpreted either unintentionally or intentionally guided by (some kind of) awareness, uncertainty, or offensive purposes. This can produce implications and consequences such as societal and political polarization, and influence or alter human behaviour and beliefs. To tackle these issues corresponding to social media manipulation mechanisms like disinformation and misinformation, a diverse palette of efforts represented by governmental and social media platforms strategies, policies, and methods plus academic and independent studies and solutions are proposed. However, such solutions are based on a technical standpoint mainly on gaming or AI-based techniques and technologies, but often only consider the defender’s perspective and address in a limited way the social perspective of this phenomenon becoming single angled. To address these issues, this research combines the defenders’ perspective with the one of the offenders by (i) building a hybrid deep learning disinformation generation and detection model and (ii) capturing and proposing a set of design recommendations that could be considered when establishing patterns, requirements, and features for building future gaming and AI-based solutions for combating social media manipulation mechanisms. This is done using the Design Science Research methodology in Data Science approach aiming at enhancing security awareness and resilience against social media manipulation.

show abstract

“…Existing research into suspended accounts on Twitter spans various settings, from political elections to social movements [ 26 – 28 ]: a limitation to these studies is that their analyses are retrospective, i.e., done by querying Twitter’s Application Programming Interface (API) with a considerable delay (sometimes years) with respect to the period of activity of observed users, hence preventing the determination of when and why accounts were actually suspended, information that are not disclosed by the platform. As labeled ground truth data about legitimate and abusive accounts is not always available, researchers typically rely on labeled datasets that emerged during audits or investigations into these platforms [ 29 ]. One such example is the case of the Russian Internet Research Agency state-controlled accounts [ 30 ], whose Twitter handles were released by the US Congress; however, Twitter never disclosed how they identified such malicious actors.…”

Section: Introductionmentioning

confidence: 99%

How does Twitter account moderation work? Dynamics of account creation and suspension on Twitter during major geopolitical events

Pierri,

Luceri,

Chen

et al. 2023

EPJ Data Sci.

View full text Add to dashboard Cite

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.

show abstract

A Large-Scale Longitudinal Multimodal Dataset of State-Backed Information Operations on Twitter

Cited by 5 publications

References 8 publications

Coordinated Behavior in Information Operations on Twitter

Coordinated Behavior in Information Operations on Twitter

Design Lessons from Building Deep Learning Disinformation Generation and Detection Solutions

How does Twitter account moderation work? Dynamics of account creation and suspension on Twitter during major geopolitical events

Contact Info

Product

Resources

About