Detection of fickle trolls in large-scale online social networks

Abstract

Online social networks have attracted billions of active users over the past decade. These systems play an integral role in the everyday life of many people around the world. As such, these platforms are also attractive for misinformation, hoaxes, and fake news campaigns which usually utilize social trolls and/or social bots for propagation. Detection of so-called social trolls in these platforms is challenging due to their large scale and dynamic nature where users’ data are generated and collected at the scale of multi-billion records per hour. In this paper, we focus on fickle trolls, i.e., a special type of trolling activity in which the trolls change their identity frequently to maximize their social relations. This kind of trolling activity may become irritating for the users and also may pose a serious threat to their privacy. To the best of our knowledge, this is the first work that introduces mechanisms to detect these trolls. In particular, we discuss and analyze troll detection mechanisms on different scales. We prove that the order of centralized single-machine detection algorithm is $$O(n^3)$$ O ( n 3 ) which is slow and impractical for early troll detection in large-scale social platforms comprising of billions of users. We also prove that the streaming approach where data is gradually fed to the system is not practical in many real-world scenarios. In light of such shortcomings, we then propose a massively parallel detection approach. Rigorous evaluations confirm that our proposed method is at least six times faster compared to conventional parallel approaches.

MetaTroll: Few-shot Detection of State-Sponsored Trolls with Transformer Adapters

“…More recently, approaches that combine user posts and online activities for troll detection have emerged [1,3,4,13,20,32,34]. Addawood et al [1] identify 49 linguistic markers of deception and measure their use by troll accounts.…”

“…), and linguistic features to identify active trolls on Twitter. Shafiei and Dadlani [32] show that Russian trolls aim to hijack the political conversation to create distrust among different groups in the community. Stewart and Dawson [34] similarly demonstrate how trolls act to accentuate disagreement and sow division along divergent frames, and this is further validated by Dutt et al [13] in relation to Russian ads on Facebook.…”

Lying in online social networks: a bug or a feature

“…This can make it easier for false information to spread rapidly, sometimes before it can be effectively fact-checked or debunked. Another factor is the vulnerability of any technological phenomenon against malware (Shafiei and Dadlani, 2022). For instance, social media platforms can be used by trolls or bots, which are fake or automated accounts that are designed to spread false information or disrupt conversations (Eberwein et al , 2017).…”