Reading Between the Lines: A Prototype Model for Detecting Twitter Sockpuppet Accounts Using Language-Agnostic Processes

Crabb, Erin Smith; Mishler, Alan; Paletz, Susannah B. F.; Hefright, Brook; Golonka, Ewa M.

doi:10.1007/978-3-319-21380-4_111

Cited by 7 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sockpuppet accounts are a long-standing phenomenon on websites and platforms that afford anonymity ( Stone and Richtel, 2007 ). On Twitter, sockpuppets typically present as anonymous accounts, often with fabricated profiles using images taken from the web, that distort and manipulate public opinion by showing support and/or opposition to products, people, or events ( Crabb et al, 2015 ). To undertake analysis of highly active sockpuppet accounts in our dataset, we developed a binary schema to deductively code each account into two categories: ‘authentic’ and ‘sockpuppet’.…”

Section: Data Collection and Methodsmentioning

confidence: 99%

#IStandWithDan versus #DictatorDan: the polarised dynamics of Twitter discussions about Victoria’s COVID-19 restrictions

Graham

Bruns

Angus

et al. 2020

Media International Australia

View full text Add to dashboard Cite

In this article, we examine two interrelated hashtag campaigns that formed in response to the Victorian State Government’s handling of Australia’s most significant COVID-19 second wave of mid-to-late 2020. Through a mixed-methods approach that includes descriptive statistical analysis, qualitative content analysis, network analysis, computational sentiment analysis and social bot detection, we reveal how a small number of hyper-partisan pro- and anti-government campaigners were able to mobilise ad hoc communities on Twitter, and – in the case of the anti-government hashtag campaign – co-opt journalists and politicians through a multi-step flow process to amplify their message. Our comprehensive analysis of Twitter data from these campaigns offers insights into the evolution of political hashtag campaigns, how actors involved in these specific campaigns were able to exploit specific dynamics of Twitter and the broader media and political establishment to progress their hyper-partisan agendas, and the utility of mixed-method approaches in helping render the dynamics of such campaigns visible.

show abstract

Section: Data Collection and Methodsmentioning

confidence: 99%

#IStandWithDan versus #DictatorDan: the polarised dynamics of Twitter discussions about Victoria’s COVID-19 restrictions

Graham

Bruns

Angus

et al. 2020

Media International Australia

View full text Add to dashboard Cite

show abstract

“…Crabb et al [20] employed a character n-gram approach for sockpuppet detection. A naive Bayes classifier was constructed using normalized frequencies of parsed character bigrams to contrast the use of writer bigram.…”

Section: Sockpuppet Detectionmentioning

confidence: 99%

Social Media Identity Deception Detection: A Survey

Alharbi,

Dong,

et al. 2021

Preprint

View full text Add to dashboard Cite

Social media have been growing rapidly and become essential elements of many people's lives. Meanwhile, social media have also come to be a popular source for identity deception. Many social media identity deception cases have arisen over the past few years. Recent studies have been conducted to prevent and detect identity deception. This survey analyses various identity deception attacks, which can be categorized into fake profile, identity theft and identity cloning. This survey provides a detailed review of social media identity deception detection techniques. It also identifies primary research challenges and issues in the existing detection techniques. This article is expected to benefit both researchers and social media providers.CCS Concepts: • Security and privacy → Social engineering attacks; Social network security and privacy.

show abstract

“…Such filtering may happen at two levels-first at a thematic level, to exclude comments that do not fit the researcher's criteria, and second, to exclude those that prima facie appear authentic but may be fabricated. Recent studies (Crabb et al, 2015;Freelon et al, 2020;Graham et al, 2020) have highlighted the concern of highly organized online activists who can influence and contaminate data with the use of bots (automated content creation tools), spam (mass communication messaging), and "sockpuppets" (a fake account designed to distort and manipulate public opinion). Despite acknowledging the challenges in using social media data, few studies have explored this process and how it may be applied effectively in practice (Graham et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

Lots of bots or maybe nots: A process for detecting bots in social media research

Mehmet

Callaghan²,

Lewis

2021

International Journal of Market Research

View full text Add to dashboard Cite

The use of bot messaging, that being artificially created messages, has increased since 2010. While not all bots are bad, many have been used to share extreme and divisive views on a range of topics, from policy discussion to brand electronic word of mouth. The issue with bot messaging and its prevalence is that it can affect researchers’ understanding of a topic. For example, if 25% of a dataset is fabricated, decision-making may result in a loss of profit or poor policy formation. To counteract the use of bots, this research note offers a framework to alleviate the potentially destructive nature of bot data and ensure the cleaning of data is thorough and beneficial to decision-making based on social media commentary. The framework is a four-step process, which includes thematic, automated, and characteristic identification stages. We provide three case studies to demonstrate the approach and conclude by providing key practical implications.

show abstract

Reading Between the Lines: A Prototype Model for Detecting Twitter Sockpuppet Accounts Using Language-Agnostic Processes

Cited by 7 publications

References 9 publications

#IStandWithDan versus #DictatorDan: the polarised dynamics of Twitter discussions about Victoria’s COVID-19 restrictions

#IStandWithDan versus #DictatorDan: the polarised dynamics of Twitter discussions about Victoria’s COVID-19 restrictions

Social Media Identity Deception Detection: A Survey

Lots of bots or maybe nots: A process for detecting bots in social media research

Contact Info

Product

Resources

About