Leaders or Followers? A Temporal Analysis of Tweets from IRA Trolls

Balasubramanian, Siva K.; Bilgic, Mustafa; Culotta, Aron; Hemphill, Libby; Nikolich, Anita; Shapiro, Matthew D.

doi:10.1609/icwsm.v16i1.19267

Cited by 5 publications

(3 citation statements)

References 24 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pseudo-Preference Generation Given the success paradigms of leveraging LLMs in natural language applications (Wu, Zhang, and Huang 2023), we incorporate the powerful knowledge of LLMs to retrieve user preferences from posts. Specifically, we opt for the preferred topic and emotion to represent the preference of each user from the corresponding posts since anomalous users may exploit them to achieve malicious intentions (Ghanem, Buscaldi, and Rosso 2019;Balasubramanian et al 2022). The 10 recent posts of user i are used as the prompt for LLM to generate the topic t and the emotion e used in each tweet j:…”

Section: Pre-training Stage: Learning User Preferences Via Postsmentioning

confidence: 99%

SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter

Chang,

Wang,

Peng

2024

AAAI

View full text Add to dashboard Cite

In the dynamic and rapidly evolving world of social media, detecting anomalous users has become a crucial task to address malicious activities such as misinformation and cyberbullying. As the increasing number of anomalous users improves the ability to mimic normal users and evade detection, existing methods only focusing on bot detection are ineffective in terms of capturing subtle distinctions between users. To address these challenges, we proposed SeGA, preference-aware self-contrastive learning for anomalous user detection, which leverages heterogeneous entities and their relations in the Twittersphere to detect anomalous users with different malicious strategies. SeGA utilizes the knowledge of large language models to summarize user preferences via posts. In addition, integrating user preferences with prompts as pseudo-labels for preference-aware self-contrastive learning enables the model to learn multifaceted aspects for describing the behaviors of users. Extensive experiments on the proposed TwBNT benchmark demonstrate that SeGA significantly outperforms the state-of-the-art methods (+3.5% ∼ 27.6%) and empirically validate the effectiveness of the model design and pre-training strategies. Our code and data are publicly available at https://github.com/ying0409/SeGA.

show abstract

Section: Pre-training Stage: Learning User Preferences Via Postsmentioning

confidence: 99%

SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter

Chang,

Wang,

Peng

2024

AAAI

View full text Add to dashboard Cite

show abstract

“…There is extensive research on manipulation strategies and the actors involved. For instance, adversaries including government entities employ political troll accounts to influence public opinion and sway elections (Zannettou et al 2019;Balasubramanian et al 2022). Automated accounts, and bots, amplify social media posts by reposting them (Chavoshi, Hamooni, and Mueen 2016;Elmas, Overdorf, and Aberer 2022).…”

Section: Related Work Social Media Manipulationmentioning

confidence: 99%

#TeamFollowBack: Detection & Analysis of Follow Back Accounts on Social Media

Elmas,

Randl,

Attia

2024

ICWSM

View full text Add to dashboard Cite

Follow back accounts inflate their follower counts by engaging in reciprocal followings. Such accounts manipulate the public and the algorithms by appearing more popular than they really are. Despite their potential harm, no studies have analyzed such accounts at scale. In this study, we present the first large-scale analysis of follow back accounts. We formally define follow back accounts and employ a honeypot approach to collect a dataset of such accounts on X (formerly Twitter). We discover and describe 12 communities of follow back accounts from 12 different countries, some of which exhibit clear political agenda. We analyze the characteristics of follow back accounts and report that they are newer, more engaging, and have more followings and followers. Finally, we propose a classifier for such accounts and report that models employing profile metadata and the ego network have some success, although achieving high recall is challenging. Our study enhances understanding of the follow back accounts and discovering such accounts in the wild.

show abstract

“…spammers (Herzallah, Faris, and Adwan 2018;Danilchenko, Segal, and Vilenchik 2022), fake followers (Cresci et al 2015), impersonating bots (Goga, Venkatadri, and Gummadi 2015), retweet bots (Elmas, Overdorf, and Aberer 2022), and astroturfing bots (Elmas et al 2021). Most of the research on non-automated sock puppets relies on datasets published by Twitter, such as IRA trolls (Balasubramanian et al 2022). Our work tries to break out of this pattern.…”

Section: Background Survey Of Related Workmentioning

confidence: 99%

Misleading Repurposing on Twitter

Elmas

Overdorf

Akgül

et al. 2023

ICWSM

View full text Add to dashboard Cite

We present the first in-depth and large-scale study of misleading repurposing, in which a malicious user changes the identity of their social media account via, among other things, changes to the profile attributes in order to use the account for a new purpose while retaining their followers. We propose a definition for the behavior and a methodology that uses supervised learning on data mined from the Internet Archive's Twitter Stream Grab to flag repurposed accounts. We found over 100,000 accounts that may have been repurposed. Of those, 28% were removed from the platform after 2 years, thereby confirming their inauthenticity. We also characterize repurposed accounts and found that they are more likely to be repurposed after a period of inactivity and deleting old tweets. We also provide evidence that adversaries target accounts with high follower counts to repurpose, and some make them have high follower counts by participating in follow-back schemes. The results we present have implications for the security and integrity of social media platforms, for data science studies in how historical data is considered, and for society at large in how users can be deceived about the popularity of an opinion. The data and the code is available at https://github.com/tugrulz/MisleadingRepurposing.

show abstract

Leaders or Followers? A Temporal Analysis of Tweets from IRA Trolls

Cited by 5 publications

References 24 publications

SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter

SeGA: Preference-Aware Self-Contrastive Learning with Prompts for Anomalous User Detection on Twitter

#TeamFollowBack: Detection & Analysis of Follow Back Accounts on Social Media

Misleading Repurposing on Twitter

Contact Info

Product

Resources

About