arXiv subjects

Luca Luceri

Publications and source records attributed to Luca Luceri.

65 records · Page 4Linked to original sources

arXiv2023

Retrieving false claims on Twitter during the Russia-Ukraine conflict

Nowadays, false and unverified information on social media sway individuals' perceptions during major geo-political events and threaten the quality of the whole digital information ecosystem. Since the Russian invasion of Ukraine, several fact-checking organizations have been actively involved in verifying stories related to the conflict that circulated online. In this paper, we leverage a public repository of fact-checked claims to build a methodological framework for automatically identifying false and unsubstantiated claims spreading on Twitter in February 2022. Our framework consists of two sequential models: First, the claim detection model identifies whether tweets incorporate a (false) claim among those considered in our collection. Then, the claim retrieval model matches the tweets with fact-checked information by ranking verified claims according to their relevance with the input tweet. Both models are based on pre-trained language models and fine-tuned to perform a text classification task and an information retrieval task, respectively. In particular, to validate the effectiveness of our methodology, we consider 83 verified false claims that spread on Twitter during the first week of the invasion, and manually annotate 5,872 tweets according to the claim(s) they report. Our experiments show that our proposed methodology outperforms standard baselines for both claim detection and claim retrieval. Overall, our results highlight how social media providers could effectively leverage semi-automated approaches to identify, track, and eventually moderate false information that spreads on their platforms.

cs.SI↗

arXiv2023

Propaganda and Misinformation on Facebook and Twitter during the Russian Invasion of Ukraine

Online social media represent an oftentimes unique source of information, and having access to reliable and unbiased content is crucial, especially during crises and contentious events. We study the spread of propaganda and misinformation that circulated on Facebook and Twitter during the first few months of the Russia-Ukraine conflict. By leveraging two large datasets of millions of social media posts, we estimate the prevalence of Russian propaganda and low-credibility content on the two platforms, describing temporal patterns and highlighting the disproportionate role played by superspreaders in amplifying unreliable content. We infer the political leaning of Facebook pages and Twitter users sharing propaganda and misinformation, and observe they tend to be more right-leaning than the average. By estimating the amount of content moderated by the two platforms, we show that only about 8-15% of the posts and tweets sharing links to Russian propaganda or untrustworthy sources were removed. Overall, our findings show that Facebook and Twitter are still vulnerable to abuse, especially during crises: we highlight the need to urgently address this issue to preserve the integrity of online conversations.

cs.SI↗

arXiv2023

Detecting Social Media Manipulation in Low-Resource Languages

Social media have been deliberately used for malicious purposes, including political manipulation and disinformation. Most research focuses on high-resource languages. However, malicious actors share content across countries and languages, including low-resource ones. Here, we investigate whether and to what extent malicious actors can be detected in low-resource language settings. We discovered that a high number of accounts posting in Tagalog were suspended as part of Twitter's crackdown on interference operations after the 2016 US Presidential election. By combining text embedding and transfer learning, our framework can detect, with promising accuracy, malicious users posting in Tagalog without any prior knowledge or training on malicious content in that language. We first learn an embedding model for each language, namely a high-resource language (English) and a low-resource one (Tagalog), independently. Then, we learn a mapping between the two latent spaces to transfer the detection model. We demonstrate that the proposed approach significantly outperforms state-of-the-art models, including BERT, and yields marked advantages in settings with very limited training data -- the norm when dealing with detecting malicious activity in online platforms.

cs.SI↗

arXiv2021

The Virtual Emotion Loop: Towards Emotion-Driven Services via Virtual Reality

The importance of emotions in service and in product design is well known. However, it is still not very well understood how users' emotions can be incorporated in a product or service lifecycle. We argue that this gap is due to a lack of a methodological framework for an effective investigation of the emotional response of persons when using products and services. Indeed, the emotional response of users is generally investigated by means of methods (e.g., surveys) that are not effective for this purpose. In our view, Virtual Reality (VR) technologies represent the perfect medium to evoke and recognize users' emotional response, as well as to prototype products and services (and, for the latter, even deliver them). In this paper, we first provide our definition of emotion-driven services, and then we propose a novel methodological framework, referred to as the Virtual-Reality-Based Emotion-Elicitation-and-Recognition loop (VEE-loop), that can be exploited to realize it. Specifically, the VEE-loop consists in a continuous monitoring of users' emotions, which are then provided to service designers as an implicit users' feedback. This information is used to dynamically change the content of the VR environment, until the desired affective state is solicited. Finally, we discuss issues and opportunities of this VEE-loop, and we also present potential applications of the VEE-loop in research and in various application areas.

cs.HC↗

arXiv2020

Down the bot hole: actionable insights from a 1-year analysis of bots activity on Twitter

Nowadays, social media represent persuasive tools that have been progressively weaponized to affect people's 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 the 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 (bot vs. human) 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 since the year before the election. Our analysis, on the horizon of the upcoming U.S. 2020 Presidential Election, reveals both alarming findings of humans' susceptibility to bots and actionable insights that can contribute to curbing coordinated campaigns.

cs.SI↗

arXiv2020

Detecting Troll Behavior via Inverse Reinforcement Learning: A Case Study of Russian Trolls in the 2016 US Election

Since the 2016 US Presidential election, social media abuse has been eliciting massive concern in the academic community and beyond. Preventing and limiting the malicious activity of users, such as trolls and bots, in their manipulation campaigns is of paramount importance for the integrity of democracy, public health, and more. However, the automated detection of troll accounts is an open challenge. In this work, we propose an approach based on Inverse Reinforcement Learning (IRL) to capture troll behavior and identify troll accounts. We employ IRL to infer a set of online incentives that may steer user behavior, which in turn highlights behavioral differences between troll and non-troll accounts, enabling their accurate classification. As a study case, we consider the troll accounts identified by the US Congress during the investigation of Russian meddling in the 2016 US Presidential election. We report promising results: the IRL-based approach is able to accurately detect troll accounts (AUC=89.1%). The differences in the predictive features between the two classes of accounts enables a principled understanding of the distinctive behaviors reflecting the incentives trolls and non-trolls respond to.

cs.SI↗

arXiv2019

Infringement of Tweets Geo-Location Privacy: an approach based on Graph Convolutional Neural Networks

The tremendous popularity gained by Online Social Networks (OSNs) raises natural concerns about user privacy in social media platforms. Though users in OSNs can tune their privacy by deliberately deciding what to share, the interaction with other individuals within the social network can expose, and eventually disclose, sensitive information. Among all the sharable personal data, geo-location is particularly interesting. On one hand, users tend to consider their current location as a very sensitive information, avoiding to share it most of the time. On the other hand, service providers are interested to extract and utilize geo-tagged data to offer tailored services. In this work, we consider the problem of inferring the current location of a user utilizing only the available information of other social contacts in the OSN. For this purpose, we employ a graph-based deep learning architecture to learn a model between the users' known and unknown geo-location during a considered period of time. As a study case, we consider Twitter, where the user generated content (i.e., tweet) can embed user's current location. Our experiments validate our approach and further confirm the concern related to data privacy in OSNs. Results show the presence of a critical-mass phenomenon, i.e., if at least 10% of the users provide their tweets with geo-tags, then the privacy of all the remaining users is seriously put at risk. In fact, our approach is able to localize almost 50% of the tweets with an accuracy below 1km relying only on a small percentage of available information.

cs.SI↗

arXiv2019

Red Bots Do It Better: Comparative Analysis of Social Bot Partisan Behavior

Recent research brought awareness of the issue of bots on social media and the significant risks of mass manipulation of public opinion in the context of political discussion. In this work, we leverage Twitter to study the discourse during the 2018 US midterm elections and analyze social bot activity and interactions with humans. We collected 2.6 million tweets for 42 days around the election day from nearly 1 million users. We use the collected tweets to answer three research questions: (i) Do social bots lean and behave according to a political ideology? (ii) Can we observe different strategies among liberal and conservative bots? (iii) How effective are bot strategies? We show that social bots can be accurately classified according to their political leaning and behave accordingly. Conservative bots share most of the topics of discussion with their human counterparts, while liberal bots show less overlap and a more inflammatory attitude. We studied bot interactions with humans and observed different strategies. Finally, we measured bots embeddedness in the social network and the effectiveness of their activities. Results show that conservative bots are more deeply embedded in the social network and more effective than liberal bots at exerting influence on humans.

cs.SI↗

arXiv2019

Perils and Challenges of Social Media and Election Manipulation Analysis: The 2018 US Midterms

One of the hallmarks of a free and fair society is the ability to conduct a peaceful and seamless transfer of power from one leader to another. Democratically, this is measured in a citizen population's trust in the electoral system of choosing a representative government. In view of the well documented issues of the 2016 US Presidential election, we conducted an in-depth analysis of the 2018 US Midterm elections looking specifically for voter fraud or suppression. The Midterm election occurs in the middle of a 4 year presidential term. For the 2018 midterms, 35 senators and all the 435 seats in the House of Representatives were up for re-election, thus, every congressional district and practically every state had a federal election. In order to collect election related tweets, we analyzed Twitter during the month prior to, and the two weeks following, the November 6, 2018 election day. In a targeted analysis to detect statistical anomalies or election interference, we identified several biases that can lead to wrong conclusions. Specifically, we looked for divergence between actual voting outcomes and instances of the #ivoted hashtag on the election day. This analysis highlighted three states of concern: New York, California, and Texas. We repeated our analysis discarding malicious accounts, such as social bots. Upon further inspection and against a backdrop of collected general election-related tweets, we identified some confounding factors, such as population bias, or bot and political ideology inference, that can lead to false conclusions. We conclude by providing an in-depth discussion of the perils and challenges of using social media data to explore questions about election manipulation.

cs.SI↗

arXiv2018

On the Social Influence in Human Behavior: Physical, Homophily, and Social Communities

Understanding the forces governing human behavior and social dynamics is a challenging problem. Individuals' decisions and actions are affected by interlaced factors, such as physical location, homophily, and social ties. In this paper, we propose to examine the role that distinct communities, linked to these factors, play as sources of social influence. The ego network is typically used in the social influence analysis. Our hypothesis is that individuals are embedded in communities not only related to their direct social relationships, but that involve different and complex forces. We analyze physical, homophily, and social communities to evaluate their relation with subjects' behavior. We prove that social influence is correlated with these communities, and each one of them is (differently) significant for individuals. We define community-based features, which reflect the subject involvement in these groups, and we use them with a supervised learning algorithm to predict subject participation in social events. Results indicate that both communities and ego network are relevant sources of social influence, confirming that the ego network alone is not sufficient to explain this phenomenon. Moreover, we classify users according to the degree of social influence they experienced with respect to their groups, recognizing classes of behavioral phenotypes. To our knowledge, this is the first work that proves the existence of phenotypes related to the social influence phenomenon.

cs.SI↗

arXiv2018

Social Influence (Deep) Learning for Human Behavior Prediction

Influence propagation in social networks has recently received large interest. In fact, the understanding of how influence propagates among subjects in a social network opens the way to a growing number of applications. Many efforts have been made to quantitatively measure the influence probability between pairs of subjects. Existing approaches have two main drawbacks: (i) they assume that the influence probabilities are independent of each other, and (ii) they do not consider the actions not performed by the subject (but performed by her/his friends) to learn these probabilities. In this paper, we propose to address these limitations by employing a deep learning approach. We introduce a Deep Neural Network (DNN) framework that has the capability for both modeling social influence and for predicting human behavior. To empirically validate the proposed framework, we conduct experiments on a real-life (offline) dataset of an Event-Based Social Network (EBSN). Results indicate that our approach outperforms existing solutions, by efficiently resolving the limitations previously described.

cs.SI↗