The Paradigm-Shift of Social Spambots

Abstract

Recent studies in social media spam and automation provide anecdotal argumentation of the rise of a new generation of spambots, so-called social spambots. Here, for the first time, we extensively study this novel phenomenon on Twitter and we provide quantitative evidence that a paradigm-shift exists in spambot design. First, we measure current Twitter's capabilities of detecting the new social spambots. Later, we assess the human performance in discriminating between genuine accounts, social spambots, and traditional spambots. Then, we benchmark several state-of-the-art techniques proposed by the academic literature. Results show that neither Twitter, nor humans, nor cutting-edge applications are currently capable of accurately detecting the new social spambots. Our results call for new approaches capable of turning the tide in the fight against this raising phenomenon. We conclude by reviewing the latest literature on spambots detection and we highlight an emerging common research trend based on the analysis of collective behaviors. Insights derived from both our extensive experimental campaign and survey shed light on the most promising directions of research and lay the foundations for the arms race against the novel social spambots. Finally, to foster research on this novel phenomenon, we make publicly available to the scientific community all the datasets used in this study.

Arming the public with artificial intelligence to counter social bots

“…Not surprisingly, hybrid approaches that mix human and automated activity have been devised to bypass bot and bot‐coordination detection systems (Grimme, Assenmacher, & Adam, ). A recent study by Cresci, Di Pietro, Petrocchi, Spognardi, and Tesconi () shows that neither humans nor supervised machine learning algorithms can identify this kind of bots successfully.…”

“…While supervised methods have proven to be effective in many cases, they do not perform well at detecting coordinated social bots that post human‐generated content (Chen & Subramanian, ; Cresci et al, ; Grimme et al, ). As mentioned earlier, those coordinated bots are not usually suspicious when considered individually.…”

A network topology approach to bot classification

“…DNA sequencing creates a set of similarity curves to which honest and dishonest nodes adhere. The approach has a 92.9% accuracy [7].…”

“…There are some notable new developments since the review of Ferrara et al [15]. Inspired by digital DNA sequencing, Cresci et al [7] developed 'Social Fingerprinting' as a way to classify bots and human agents. DNA sequencing creates a set of similarity curves to which honest and dishonest nodes adhere.…”

“…These objectives play well into the political arena, where the popularity and credibility of personalities and ideas are of central concern. Cresci et al [7] argue that there is evidence of a new paradigm in bot development, which they term 'social bots'. This new wave of bots are smarter and have more advanced objectives.…”