A socialbots analysis-driven graph-based approach for identifying coordinated campaigns in twitter

Fazil, Mohd; Abulaish, Muhammad

doi:10.3233/jifs-182895

Cited by 15 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Examples of valid options are the cosine similarity between user feature vectors encoding account profile characteristics, as done in (Fazil and Abulaish 2020), or the Jaccard similarity between the sets of hashtags used by each user, or between the sets of followings or retweeted accounts.…”

Section: Methods Overviewmentioning

confidence: 99%

“…In addition, they also develop an astroturfing detection methodology based on the previously identified coordination patterns. In (Fazil and Abulaish 2020) is proposed a multi-attributed graph-based approach for detecting CIB in Twitter. Authors model each user with a 6-dimensional feature vector, compute pairwise similarities obtaining a user-similarity graph and finally ap-ply Markov clustering, labeling the resulting clusters as inauthentic coordinated groups.…”

Section: Related Workmentioning

confidence: 99%

“…Authors model each user with a 6-dimensional feature vector, compute pairwise similarities obtaining a user-similarity graph and finally ap-ply Markov clustering, labeling the resulting clusters as inauthentic coordinated groups. In (Fazil and Abulaish 2020), high coordination automatically implies inauthenticity.…”

Section: Related Workmentioning

confidence: 99%

“…Instead of proposing a new technique, the study in (Vargas, Emami, and Traynor 2020) focuses on determining the usefulness and reliability of previously-proposed networkbased metrics of coordination. Several authors, including some of those previously mentioned, report positive results for the detection of inauthentic behavior via the analysis of suspicious coordination (Ratkiewicz et al 2011;Keller et al 2020;Fazil and Abulaish 2020). However, the results of (Vargas, Emami, and Traynor 2020) show that, when evaluated in non-trivial real-world scenarios, such previously proposed approaches are unable to distinguish between authentic (e.g., activists, fandoms) and inauthentic coordination.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Coordinated Behavior on Social Media in 2019 UK General Election

Nizzoli¹,

Tardelli²,

Avvenuti³

et al. 2020

Preprint

View full text Add to dashboard Cite

Coordinated online behaviors are an important part of information and influence operations, as they allow a more effective disinformation's spread. Most studies on coordinated behaviors involved manual investigations and the few existing computational approaches make bold assumptions or oversimplify the problem to make it tractable.Here, we propose a new network-based framework for uncovering and studying coordinated behaviors on social media. Our proposal extends existing systems and goes beyond limiting binary classifications of coordinated and uncoordinated behaviors. It allows to uncover different patterns of coordination and to estimate the degree of coordination that characterizes different communities. We apply our framework to a dataset collected during the 2019 UK General Election, detecting and characterizing coordinated communities that participated in the electoral debate. Our work conveys both theoretical and practical implications, and provides more nuanced and fine-grained results for studying online manipulation.

show abstract

Section: Methods Overviewmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Coordinated Behavior on Social Media in 2019 UK General Election

Nizzoli¹,

Tardelli²,

Avvenuti³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Here, challenges include the limited availability of data itself, missing or ambiguous ground truth and the obsolescence of existing datasets that hardly cope with the rapid evolution of malicious accounts. To this regard, continuous data-sharing initiatives such as that of Twitter for accounts involved in information operations 12 , are extremely welcome as they can enable the next wave of research on these issues. Then, we should also devise additional ways for creating a broad array of diverse adversarial examples.…”

Section: Open Challenges and The Way Aheadmentioning

confidence: 99%

A Decade of Social Bot Detection

Cresci

2020

Preprint

View full text Add to dashboard Cite

Ratkiewicz et al. "Detecting and tracki..." Proc. ICWSM. Dickerson et al. "Using sentiment to..." Proc. ASONAM. Abokhodair et al. "Dissecting a s..." Proc. ACM CSCW. Cerón-Guzmán et al. "Detecting social ..." Proc. MICAI. Forelle et al. "Political bots a..." OII COMPROP Report. Bastos et al. "The Brexit b..." Soc Sci Comp Rev 37(1). Hegelich et al. "Are social bots on Twi..." Proc. ICWSM. Gorwa "Computational propa..." OII COMPROP Report. Keller et al. "How to manipulate social..." Proc. ICWSM. McKelvey et al. "Computatio..." OII COMPROP Report. Neudert et al. "Junk news an..." OII COMPROP Report. Schäfer et al. "Japan's 2014 General ..." Big Data 5(4). Stukal et al. "Detecting bots on Russia..." Big Data 5(4). Fernquist et al. "Political bots and th..." Proc. IEEE ISI. Schuchard et al. "Bots in n..." Proc. Complex Networks. Bolsover et al. "Chinese co..." Inf, Comm & Soc 22(14). Luceri et al. "Red bots do it bette..." Proc. WWW Comp.

show abstract