Exposing influence campaigns in the age of LLMs: a behavioral-based AI approach to detecting state-sponsored trolls.

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.

How does Twitter account moderation work? Dynamics of account creation and suspension on Twitter during major geopolitical events.

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.

Artificial Intelligence and Cardiovascular Risk Prediction: All That Glitters is not Gold.

Artificial intelligence (AI) is a broad term referring to any automated systems that need 'intelligence' to carry out specific tasks. During the last decade, AI-based techniques have been gaining popularity in a vast range of biomedical fields, including the cardiovascular setting. Indeed, the dissemination of cardiovascular risk factors and the better prognosis of patients experiencing cardiovascular events resulted in an increase in the prevalence of cardiovascular disease (CVD), eliciting the need for precise identification of patients at increased risk for development and progression of CVD. AI-based predictive models may overcome some of the limitations that hinder the performance of classic regression models. Nonetheless, the successful application of AI in this field requires knowledge of the potential pitfalls of the AI techniques, to guarantee their safe and effective use in daily clinical practice. The aim of the present review is to summarise the pros and cons of different AI methods and their potential application in the cardiovascular field, with a focus on the development of predictive models and risk assessment tools.

Misinformation, manipulation, and abuse on social media in the era of COVID-19.

The COVID-19 pandemic represented an unprecedented setting for the spread of online misinformation, manipulation, and abuse, with the potential to cause dramatic real-world consequences. The aim of this special issue was to collect contributions investigating issues such as the emergence of infodemics, misinformation, conspiracy theories, automation, and online harassment on the onset of the coronavirus outbreak. Articles in this collection adopt a diverse range of methods and techniques, and focus on the study of the narratives that fueled conspiracy theories, on the diffusion patterns of COVID-19 misinformation, on the global news sentiment, on hate speech and social bot interference, and on multimodal Chinese propaganda. The diversity of the methodological and scientific approaches undertaken in the aforementioned articles demonstrates the interdisciplinarity of these issues. In turn, these crucial endeavors might anticipate a growing trend of studies where diverse theories, models, and techniques will be combined to tackle the different aspects of online misinformation, manipulation, and abuse.

A Cooperative Machine Learning Approach for Pedestrian Navigation in Indoor IoT.

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.