Search

The detection of state-sponsored trolls operating in influence campaigns on social media is a critical and unsolved challenge for the research community, which has significant implications beyond the online realm. To address this challenge, we propose a new AI-based solution that identifies troll accounts solely through behavioral cues associated with their sequences of sharing activity, encompassing both their actions and the feedback they receive from others. Our approach does not incorporate any textual content shared and consists of two steps: First, we leverage an LSTM-based classifier to determine whether account sequences belong to a state-sponsored troll or an organic, legitimate user. Second, we employ the classified sequences to calculate a metric named the "Troll Score", quantifying the degree to which an account exhibits troll-like behavior. To assess the effectiveness of our method, we examine its performance in the context of the 2016 Russian interference campaign during the U.S. Presidential election. Our experiments yield compelling results, demonstrating that our approach can identify account sequences with an AUC close to 99% and accurately differentiate between Russian trolls and organic users with an AUC of 91%. Notably, our behavioral-based approach holds a significant advantage in the ever-evolving landscape, where textual and linguistic properties can be easily mimicked by Large Language Models (LLMs): In contrast to existing language-based techniques, it relies on more challenging-to-replicate behavioral cues, ensuring greater resilience in identifying influence campaigns, especially given the potential increase in the usage of LLMs for generating inauthentic content. Finally, we assessed the generalizability of our solution to various entities driving different information operations and found promising results that will guide future research. [ABSTRACT FROM AUTHOR]

Social media moderation policies are often at the center of public debate, and their implementation and enactment are sometimes surrounded by a veil of mystery. Unsurprisingly, due to limited platform transparency and data access, relatively little research has been devoted to characterizing moderation dynamics, especially in the context of controversial events and the platform activity associated with them. Here, we study the dynamics of account creation and suspension on Twitter during two global political events: Russia's invasion of Ukraine and the 2022 French Presidential election. Leveraging a large-scale dataset of 270M tweets shared by 16M users in multiple languages over several months, we identify peaks of suspicious account creation and suspension, and we characterize behaviors that more frequently lead to account suspension. We show how large numbers of accounts get suspended within days of their creation. Suspended accounts tend to mostly interact with legitimate users, as opposed to other suspicious accounts, making unwarranted and excessive use of reply and mention features, and sharing large amounts of spam and harmful content. While we are only able to speculate about the specific causes leading to a given account suspension, our findings contribute to shedding light on patterns of platform abuse and subsequent moderation during major events. [ABSTRACT FROM AUTHOR]

Information operations (IOs) pose a significant threat to the integrity of democratic processes, with the potential to influence election-related online discourse. In anticipation of the 2024 U.S. presidential election, we present a study aimed at uncovering the digital traces of coordinated IOs on X (formerly Twitter). Using our machine learning framework for detecting online coordination, we analyze a dataset comprising election-related conversations on X from May to July 2024. This reveals a network of coordinated inauthentic actors, displaying notable similarities in their link-sharing behaviors. Our analysis shows concerted efforts by these accounts to disseminate misleading, redundant, and biased information across the Web through a coordinated cross-platform information operation: The links shared by this network frequently direct users to other social media platforms or mock news sites featuring low-quality political content and, in turn, promoting the same X and YouTube accounts. Members of this network also shared deceptive images generated by AI, accompanied by language attacking political figures and symbolic imagery intended to convey power and dominance. While X has suspended or restricted a subset of these accounts, 75 percent of the coordinated network remains active, garnering substantial traction over time: The suspicious Web sites promoted by this coordinated network are shared thousands of times per day by the X user base, further amplifying their reach and potential impact. Our findings underscore the critical role of developing computational models to scale up the detection of threats on large social media platforms, and emphasize the broader implications of these techniques to detect IOs across the wider Web. [ABSTRACT FROM AUTHOR]

Social media represent persuasive tools that have been progressively weaponized to affect beliefs, spread manipulative narratives, and sow conflicts along divergent factions. Software-controlled accounts (i.e., bots) are one of the main actors associated with manipulation campaigns, especially in a political context. Uncovering the strategies behind bots' activities is of paramount importance to detect and curb such campaigns. In this paper, we present a long term (one year) analysis of bots activity on Twitter in the run-up to the 2018 U.S. midterm elections. We identify different classes of accounts based on their nature (human vs. bot) and engagement within the online discussion and we observe that hyperactive bots played a pivotal role in the dissemination of conspiratorial narratives, while dominating the political debate in the year before the election. Our analysis, in advance of the U.S. 2020 presidential election, reveals both alarming findings of human susceptibility to bots and actionable insights that can contribute to curbing coordinated campaigns. [ABSTRACT FROM AUTHOR]

This paper presents a system based on pedestrian dead reckoning (PDR) for localization of networked mobile users, which relies only on sensors embedded in the devices and device- to-device connectivity. The user trajectory is reconstructed by measuring step by step the user displacements. Though step length can be estimated rather accurately, heading evaluation is extremely problematic in indoor environments. Magnetometer is typically used, however measurements are strongly perturbed. To improve the location accuracy, this paper proposes a novel cooperative system to estimate the direction of motion based on a machine learning approach for perturbation detection and filtering, combined with a consensus algorithm for performance augmentation by cooperative data fusion at multiple devices. A first algorithm filters out perturbed magnetometer measurements based on a-priori information on the Earth's magnetic field. A second algorithm aggregates groups of users walking in the same direction, while a third one combines the measurements of the aggregated users in a distributed way to extract a more accurate heading estimate. To the best of our knowledge, this is the first approach that combines machine learning with consensus algorithms for cooperative PDR. Compared to other methods in the literature, the method has the advantage of being infrastructure-free, fully distributed and robust to sensor failures thanks to the pre-filtering of perturbed measurements. Extensive indoor experiments show that the heading error is highly reduced by the proposed approach thus leading to noticeable enhancements in localization performance. [ABSTRACT FROM AUTHOR]

Online social media have become one of the main communication platforms for political discussion. The online ecosystem, however, does not only include human users but has given a space to an increasing number of automated accounts, referred to as bots, extensively used to spread messages and manipulate the narratives others are exposed to. Although social media service providers put increasing efforts to protect their platforms, malicious bot accounts continuously evolve to escape detection. In this work, we monitored the activity of almost 245K accounts engaged in the Twitter political discussion during the last two U.S. voting events. We identified approximately 31K bots and characterized their activity in contrast with humans. We show that, in the 2018 midterms, bots changed the volume and the temporal dynamics of their online activity to better mimic humans and avoid detection. Our findings highlight the mutable nature of bots and illustrate the challenges to forecast their evolution. [ABSTRACT FROM AUTHOR]