Fake (Sybil) Account Detection Using Machine Learning

Singh, Yeshwant; Banerjee, Subhasish

doi:10.2139/ssrn.3462933

“…Social bots and their effects have been studied in the context of political manipulation and misinformation, such as for presidential campaigns (Shao et al, 2017), distorting online discussion in presidential election (Bessi & Ferrara, 2016), influencing public opinion (Ross et al, 2019) or fabricating collective action (Francois et al, 2018). The majority of analysis and computational work on social bots have been mostly concentrated on how to detect bot accounts (Cao et al, 2012;Chavoshi et al, 2016;Chu et al, 2012;Davis et al, 2016;Luo et al, 2020;Mazza et al, 2019;Singh, & Banerjee, 2019;Wang et al, 2012) as discussed in detail in Chapter…”

Section: Chapter Five: Affordances and Social Botsmentioning

confidence: 99%

Bot Politics: The Affordances of Twitter and Nonhuman Participation

Momeni

2024

Preprint

0

View full text Add to dashboard Cite

Social networking sites have had an indisputable impact on the realm of political communications, increasing political discourses all around the world. Social media platforms offer some affordances that can be employed by users to facilitate their political activism. However, online political activism can be influenced by software robots which can interact on social media to emulate human users’ behaviour and influence their political opinion. This dissertation employs the theory of affordances and explores how the affordances of Twitter, including shareability, direct communication, dynamic interaction, searchability, and identifiability function in practice and have been used to facilitate the political engagement of human and nonhuman users. To do so, this dissertation uses the case study of the 2017 Women’s March in the United States to articulate the affordances of Twitter and explores how human users employ the affordances of this platform in their political engagement. The result of this analysis indicates that the affordances of Twitter such as shareability (tweeting, retweeting, hashtags), and dynamic interaction (liking) were the most prevalent affordances of this platform during the Women’s March. In addition, the case study of “building the wall” is used to analyze social bots’ function, behaviour, and interaction on Twitter, to demonstrate to what extend bots are capable of using the affordances of Twitter. This study demonstrates that bots use the affordance of shareability (retweeting) and dynamic interaction (liking) more than other affordances. However, this study did not find convincing evidence that these bots are able to generate new content, cultivate meaningful discussions, or directly provide responses to other tweets. The theory of affordances accredits two main components, the human and the environment, and claims that affordances are properties that the environment offers to any human who perceives and uses them. However, focusing on two main elements creates substantial limitations for employing the theory to explore artificial intelligence and self-improving machines. This study demonstrates that bots are capable of using some of the affordances of Twitter and imitate human-like performance to some degree. Therefore, by including a third component — nonhuman smart actors— this study proposes a new definition for the theory of affordances, which is a core contribution of this dissertation.

show abstract

“…Social bots and their effects have been studied in the context of political manipulation and misinformation, such as for presidential campaigns (Shao et al, 2017), distorting online discussion in presidential election (Bessi & Ferrara, 2016), influencing public opinion (Ross et al, 2019) or fabricating collective action (Francois et al, 2018). The majority of analysis and computational work on social bots have been mostly concentrated on how to detect bot accounts (Cao et al, 2012;Chavoshi et al, 2016;Chu et al, 2012;Davis et al, 2016;Luo et al, 2020;Mazza et al, 2019;Singh, & Banerjee, 2019;Wang et al, 2012) as discussed in detail in Chapter…”

Section: Chapter Five: Affordances and Social Botsmentioning

confidence: 99%

Bot Politics: The Affordances of Twitter and Nonhuman Participation

Momeni

2024

Preprint

0

View full text Add to dashboard Cite

Social networking sites have had an indisputable impact on the realm of political communications, increasing political discourses all around the world. Social media platforms offer some affordances that can be employed by users to facilitate their political activism. However, online political activism can be influenced by software robots which can interact on social media to emulate human users’ behaviour and influence their political opinion. This dissertation employs the theory of affordances and explores how the affordances of Twitter, including shareability, direct communication, dynamic interaction, searchability, and identifiability function in practice and have been used to facilitate the political engagement of human and nonhuman users. To do so, this dissertation uses the case study of the 2017 Women’s March in the United States to articulate the affordances of Twitter and explores how human users employ the affordances of this platform in their political engagement. The result of this analysis indicates that the affordances of Twitter such as shareability (tweeting, retweeting, hashtags), and dynamic interaction (liking) were the most prevalent affordances of this platform during the Women’s March. In addition, the case study of “building the wall” is used to analyze social bots’ function, behaviour, and interaction on Twitter, to demonstrate to what extend bots are capable of using the affordances of Twitter. This study demonstrates that bots use the affordance of shareability (retweeting) and dynamic interaction (liking) more than other affordances. However, this study did not find convincing evidence that these bots are able to generate new content, cultivate meaningful discussions, or directly provide responses to other tweets. The theory of affordances accredits two main components, the human and the environment, and claims that affordances are properties that the environment offers to any human who perceives and uses them. However, focusing on two main elements creates substantial limitations for employing the theory to explore artificial intelligence and self-improving machines. This study demonstrates that bots are capable of using some of the affordances of Twitter and imitate human-like performance to some degree. Therefore, by including a third component — nonhuman smart actors— this study proposes a new definition for the theory of affordances, which is a core contribution of this dissertation.

show abstract

“…ese accounts are counterfeit accounts injected in the OSNs to spread fake news, compromise systems, or make Sybil attacks. us, with the increasing popularity of the OSNs, the fake accounts are increasing, reaching up to 3 to 4% of Facebook accounts [5]. e Sybil attacks are discussed in [5][6][7][8].…”

Section: Fake Accountsmentioning

confidence: 99%

“…With over 320 million active users, Twitter has become one of the most popular microblogging OSNs [5]. Unfortunately, there is not any publicly available standardized Twitter dataset for authorship verification studies [3].…”

Section: Collecting and Preprocessing The Datamentioning

confidence: 99%

“…So, it is crucial to introduce a Twitter dataset to facilitate authorship verification models. e way to obtain Twitter data is through its API [5]. However, Twitter allows retrieving a limited amount of data through the API, about 3200 tweets with 280 characters' block, and their related features through many batches [24].…”

Section: Collecting and Preprocessing The Datamentioning

confidence: 99%

See 1 more Smart Citation

Design and Analysis of a Novel Authorship Verification Framework for Hijacked Social Media Accounts Compromised by a Human

Alterkavı

¹

,

Erbay

²

2021

Security and Communication Networks

View full text Add to dashboard Cite

Compromising the online social network account of a genuine user, by imitating the user’s writing trait for malicious purposes, is a standard method. Then, when it happens, the fast and accurate detection of intruders is an essential step to control the damage. In other words, an efficient authorship verification model is a binary classification for the investigation of the text, whether it is written by a genuine user or not. Herein, a novel authorship verification framework for hijacked social media accounts, compromised by a human, is proposed. Significant textual features are derived from a Twitter-based dataset. They are composed of 16124 tweets with 280 characters crawled and manually annotated with the authorship information. XGBoost algorithm is then used to highlight the significance of each textual feature in the dataset. Furthermore, the ELECTRE approach is utilized for feature selection, and the rank exponent weight method is applied for feature weighting. The reduced dataset is evaluated with many classifiers, and the achieved result of the F-score is 94.4%.

show abstract

Fake (Sybil) Account Detection Using Machine Learning

Cited by 5 publications

References 0 publications

Bot Politics: The Affordances of Twitter and Nonhuman Participation

Bot Politics: The Affordances of Twitter and Nonhuman Participation

Bot Politics: The Affordances of Twitter and Nonhuman Participation

Design and Analysis of a Novel Authorship Verification Framework for Hijacked Social Media Accounts Compromised by a Human

Contact Info

Product

Resources

About