Marinella Petrocchi

Stefano Cresci, Kai-Cheng Yang, Angelo Spognardi et al.

Research on social bots aims at advancing knowledge and providing solutions to one of the most debated forms of online manipulation. Yet, social bot research is plagued by widespread biases, hyped results, and misconceptions that set the stage for ambiguities, unrealistic expectations, and seemingly irreconcilable findings. Overcoming such issues is instrumental towards ensuring reliable solutions and reaffirming the validity of the scientific method. Here, we discuss a broad set of consequential methodological and conceptual issues that affect current social bots research, illustrating each with examples drawn from recent studies. More importantly, we demystify common misconceptions, addressing fundamental points on how social bots research is discussed. Our analysis surfaces the need to discuss research about online disinformation and manipulation in a rigorous, unbiased, and responsible way. This article bolsters such effort by identifying and refuting common fallacious arguments used by both proponents and opponents of social bots research, as well as providing directions toward sound methodologies for future research.

Edoardo Di Paolo, Marinella Petrocchi, Angelo Spognardi

Online Social Networks have revolutionized how we consume and share information, but they have also led to a proliferation of content not always reliable and accurate. One particular type of social accounts is known to promote unreputable content, hyperpartisan, and propagandistic information. They are automated accounts, commonly called bots. Focusing on Twitter accounts, we propose a novel approach to bot detection: we first propose a new algorithm that transforms the sequence of actions that an account performs into an image; then, we leverage the strength of Convolutional Neural Networks to proceed with image classification. We compare our performances with state-of-the-art results for bot detection on genuine accounts / bot accounts datasets well known in the literature. The results confirm the effectiveness of the proposal, because the detection capability is on par with the state of the art, if not better in some cases.

Rocco De Nicola, Marinella Petrocchi, Manuel Pratelli

For more than a decade now, academicians and online platform administrators have been studying solutions to the problem of bot detection. Bots are computer algorithms whose use is far from being benign: malicious bots are purposely created to distribute spam, sponsor public characters and, ultimately, induce a bias within the public opinion. To fight the bot invasion on our online ecosystem, several approaches have been implemented, mostly based on (supervised and unsupervised) classifiers, which adopt the most varied account features, from the simplest to the most expensive ones to be extracted from the raw data obtainable through the Twitter public APIs. In this exploratory study, using Twitter as a benchmark, we compare the performances of four state-of-art feature sets in detecting novel bots: one of the output scores of the popular bot detector Botometer, which considers more than 1,000 features of an account to take a decision; two feature sets based on the account profile and timeline; and the information about the Twitter client from which the user tweets. The results of our analysis, conducted on six recently released datasets of Twitter accounts, hint at the possible use of general-purpose classifiers and cheap-to-compute account features for the detection of evolved bots.

Manuel Pratelli, Marinella Petrocchi

Large language models (LLMs) make it possible to generate synthetic behavioural data at scale, offering an ethical and low-cost alternative to human experiments. Whether such data can faithfully capture psychological differences driven by personality traits, however, remains an open question. We evaluate the capacity of LLM agents, conditioned on Big-Five profiles, to reproduce personality-based variation in susceptibility to misinformation, focusing on news discernment, the ability to judge true headlines as true and false headlines as false. Leveraging published datasets in which human participants with known personality profiles rated headline accuracy, we create matching LLM agents and compare their responses to the original human patterns. Certain trait-misinformation associations, notably those involving Agreeableness and Conscientiousness, are reliably replicated, whereas others diverge, revealing systematic biases in how LLMs internalize and express personality. The results underscore both the promise and the limits of personality-aligned LLMs for behavioral simulation, and offer new insight into modeling cognitive diversity in artificial agents.

Edoardo Allegrini, Edoardo Di Paolo, Angelo Spognardi et al.

BotVerse is a scalable, event-driven framework for high-fidelity social simulation using LLM-based agents. It addresses the ethical risks of studying autonomous agents on live networks by isolating interactions within a controlled environment while grounding them in real-time content streams from the Bluesky ecosystem. The system features an asynchronous orchestration API and a simulation engine that emulates human-like temporal patterns and cognitive memory. Through the Synthetic Social Observatory, researchers can deploy customizable personas and observe multimodal interactions at scale. We demonstrate BotVersevia a coordinated disinformation scenario, providing a safe, experimental framework for red-teaming and computational social scientists. A video demonstration of the framework is available at https://youtu.be/eZSzO5Jarqk.

Stefano Cresci, Marinella Petrocchi, Angelo Spognardi et al.

Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of image recognition, a stop signal can be misclassified as a speed limit indication.However, adversarial examples also represent the fuel for a flurry of research directions in different domains and applications. Here, we give an overview of how they can be profitably exploited as powerful tools to build stronger learning models, capable of better-withstanding attacks, for two crucial tasks: fake news and social bot detection.

Michela Fazzolari, Francesco Buccafurri, Gianluca Lax et al.

Over the last years, online reviews became very important since they can influence the purchase decision of consumers and the reputation of businesses, therefore, the practice of writing fake reviews can have severe consequences on customers and service providers. Various approaches have been proposed for detecting opinion spam in online reviews, especially based on supervised classifiers. In this contribution, we start from a set of effective features used for classifying opinion spam and we re-engineered them, by considering the Cumulative Relative Frequency Distribution of each feature. By an experimental evaluation carried out on real data from Yelp.com, we show that the use of the distributional features is able to improve the performances of classifiers.

Stefano Cresci, Marinella Petrocchi, Angelo Spognardi et al.

The arm race between spambots and spambot-detectors is made of several cycles (or generations): a new wave of spambots is created (and new spam is spread), new spambot filters are derived and old spambots mutate (or evolve) to new species. Recently, with the diffusion of the adversarial learning approach, a new practice is emerging: to manipulate on purpose target samples in order to make stronger detection models. Here, we manipulate generations of Twitter social bots, to obtain - and study - their possible future evolutions, with the aim of eventually deriving more effective detection techniques. In detail, we propose and experiment with a novel genetic algorithm for the synthesis of online accounts. The algorithm allows to create synthetic evolved versions of current state-of-the-art social bots. Results demonstrate that synthetic bots really escape current detection techniques. However, they give all the needed elements to improve such techniques, making possible a proactive approach for the design of social bot detection systems.

Fabio Del Vigna, Marinella Petrocchi, Alessandro Tommasi et al.

This paper considers online news censorship and it concentrates on censorship of identities. Obfuscating identities may occur for disparate reasons, from military to judiciary ones. In the majority of cases, this happens to protect individuals from being identified and persecuted by hostile people. However, being the collaborative web characterised by a redundancy of information, it is not unusual that the same fact is reported by multiple sources, which may not apply the same restriction policies in terms of censorship. Also, the proven aptitude of social network users to disclose personal information leads to the phenomenon that comments to news can reveal the data withheld in the news itself. This gives us a mean to figure out who the subject of the censored news is. We propose an adaptation of a text analysis approach to unveil censored identities. The approach is tested on a synthesised scenario, which however resembles a real use case. Leveraging a text analysis based on a context classifier trained over snippets from posts and comments of Facebook pages, we achieve promising results. Despite the quite constrained settings in which we operate -- such as considering only snippets of very short length -- our system successfully detects the censored name, choosing among 10 different candidate names, in more than 50\% of the investigated cases. This outperforms the results of two reference baselines. The findings reported in this paper, other than being supported by a thorough experimental methodology and interesting on their own, also pave the way for further investigation on the insidious issues of censorship on the web.

Michela Fazzolari, Vittoria Cozza, Marinella Petrocchi et al.

In this paper, we focus on online reviews and employ artificial intelligence tools, taken from the cognitive computing field, to help understanding the relationships between the textual part of the review and the assigned numerical score. We move from the intuitions that 1) a set of textual reviews expressing different sentiments may feature the same score (and vice-versa); and 2) detecting and analyzing the mismatches between the review content and the actual score may benefit both service providers and consumers, by highlighting specific factors of satisfaction (and dissatisfaction) in texts. To prove the intuitions, we adopt sentiment analysis techniques and we concentrate on hotel reviews, to find polarity mismatches therein. In particular, we first train a text classifier with a set of annotated hotel reviews, taken from the Booking website. Then, we analyze a large dataset, with around 160k hotel reviews collected from Tripadvisor, with the aim of detecting a polarity mismatch, indicating if the textual content of the review is in line, or not, with the associated score. Using well established artificial intelligence techniques and analyzing in depth the reviews featuring a mismatch between the text polarity and the score, we find that -on a scale of five stars- those reviews ranked with middle scores include a mixture of positive and negative aspects. The approach proposed here, beside acting as a polarity detector, provides an effective selection of reviews -on an initial very large dataset- that may allow both consumers and providers to focus directly on the review subset featuring a text/score disagreement, which conveniently convey to the user a summary of positive and negative features of the review target.

Michela Fazzolari, Marinella Petrocchi, Alessandro Tommasi et al.

In this paper, we propose a novel approach for aggregating online reviews, according to the opinions they express. Our methodology is unsupervised - due to the fact that it does not rely on pre-labeled reviews - and it is agnostic - since it does not make any assumption about the domain or the language of the review content. We measure the adherence of a review content to the domain terminology extracted from a review set. First, we demonstrate the informativeness of the adherence metric with respect to the score associated with a review. Then, we exploit the metric values to group reviews, according to the opinions they express. Our experimental campaign has been carried out on two large datasets collected from Booking and Amazon, respectively.

Stefano Cresci, Roberto Di Pietro, Marinella Petrocchi et al.

Spambot detection in online social networks is a long-lasting challenge involving the study and design of detection techniques capable of efficiently identifying ever-evolving spammers. Recently, a new wave of social spambots has emerged, with advanced human-like characteristics that allow them to go undetected even by current state-of-the-art algorithms. In this paper, we show that efficient spambots detection can be achieved via an in-depth analysis of their collective behaviors exploiting the digital DNA technique for modeling the behaviors of social network users. Inspired by its biological counterpart, in the digital DNA representation the behavioral lifetime of a digital account is encoded in a sequence of characters. Then, we define a similarity measure for such digital DNA sequences. We build upon digital DNA and the similarity between groups of users to characterize both genuine accounts and spambots. Leveraging such characterization, we design the Social Fingerprinting technique, which is able to discriminate among spambots and genuine accounts in both a supervised and an unsupervised fashion. We finally evaluate the effectiveness of Social Fingerprinting and we compare it with three state-of-the-art detection algorithms. Among the peculiarities of our approach is the possibility to apply off-the-shelf DNA analysis techniques to study online users behaviors and to efficiently rely on a limited number of lightweight account characteristics.

Fabio Del Vigna, Marinella Petrocchi, Alessandro Tommasi et al.

New Psychoactive Substances (NPS) are drugs that lay in a grey area of legislation, since they are not internationally and officially banned, possibly leading to their not prosecutable trade. The exacerbation of the phenomenon is that NPS can be easily sold and bought online. Here, we consider large corpora of textual posts, published on online forums specialized on drug discussions, plus a small set of known substances and associated effects, which we call seeds. We propose a semi-supervised approach to knowledge extraction, applied to the detection of drugs (comprising NPS) and effects from the corpora under investigation. Based on the very small set of initial seeds, the work highlights how a contrastive approach and context deduction are effective in detecting substances and effects from the corpora. Our promising results, which feature a F1 score close to 0.9, pave the way for shortening the detection time of new psychoactive substances, once these are discussed and advertised on the Internet.

Vittoria Cozza, Marinella Petrocchi, Angelo Spognardi

Automatic quality evaluation of Web information is a task with many fields of applications and of great relevance, especially in critical domains like the medical one. We move from the intuition that the quality of content of medical Web documents is affected by features related with the specific domain. First, the usage of a specific vocabulary (Domain Informativeness); then, the adoption of specific codes (like those used in the infoboxes of Wikipedia articles) and the type of document (e.g., historical and technical ones). In this paper, we propose to leverage specific domain features to improve the results of the evaluation of Wikipedia medical articles. In particular, we evaluate the articles adopting an "actionable" model, whose features are related to the content of the articles, so that the model can also directly suggest strategies for improving a given article quality. We rely on Natural Language Processing (NLP) and dictionaries-based techniques in order to extract the bio-medical concepts in a text. We prove the effectiveness of our approach by classifying the medical articles of the Wikipedia Medicine Portal, which have been previously manually labeled by the Wiki Project team. The results of our experiments confirm that, by considering domain-oriented features, it is possible to obtain sensible improvements with respect to existing solutions, mainly for those articles that other approaches have less correctly classified. Other than being interesting by their own, the results call for further research in the area of domain specific features suitable for Web data quality assessment.

Stefano Cresci, Roberto Di Pietro, Marinella Petrocchi et al.

We propose a strikingly novel, simple, and effective approach to model online user behavior: we extract and analyze digital DNA sequences from user online actions and we use Twitter as a benchmark to test our proposal. We obtain an incisive and compact DNA-inspired characterization of user actions. Then, we apply standard DNA analysis techniques to discriminate between genuine and spambot accounts on Twitter. An experimental campaign supports our proposal, showing its effectiveness and viability. To the best of our knowledge, we are the first ones to identify and adapt DNA-inspired techniques to online user behavioral modeling. While Twitter spambot detection is a specific use case on a specific social media, our proposed methodology is platform and technology agnostic, hence paving the way for diverse behavioral characterization tasks.

Mauro Conti, Vittoria Cozza, Marinella Petrocchi et al.

In the last decade, the advertisement market spread significantly in the web and mobile app system. Its effectiveness is also due thanks to the possibility to target the advertisement on the specific interests of the actual user, other than on the content of the website hosting the advertisement. In this scenario, became of great value services that collect and hence can provide information about the browsing user, like Facebook and Google. In this paper, we show how to maliciously exploit the Google Targeted Advertising system to infer personal information in Google user profiles. In particular, the attack we consider is external from Google and relies on combining data from Google AdWords with other data collected from a website of the Google Display Network. We validate the effectiveness of our proposed attack, also discussing possible application scenarios. The result of our research shows a significant practical privacy issue behind such type of targeted advertising service, and call for further investigation and the design of more privacy-aware solutions, possibly without impeding the current business model involved in online advertisement.

Stefano Cresci, Roberto Di Pietro, Marinella Petrocchi et al.

$\textit{Fake followers}$ are those Twitter accounts specifically created to inflate the number of followers of a target account. Fake followers are dangerous for the social platform and beyond, since they may alter concepts like popularity and influence in the Twittersphere - hence impacting on economy, politics, and society. In this paper, we contribute along different dimensions. First, we review some of the most relevant existing features and rules (proposed by Academia and Media) for anomalous Twitter accounts detection. Second, we create a baseline dataset of verified human and fake follower accounts. Such baseline dataset is publicly available to the scientific community. Then, we exploit the baseline dataset to train a set of machine-learning classifiers built over the reviewed rules and features. Our results show that most of the rules proposed by Media provide unsatisfactory performance in revealing fake followers, while features proposed in the past by Academia for spam detection provide good results. Building on the most promising features, we revise the classifiers both in terms of reduction of overfitting and cost for gathering the data needed to compute the features. The final result is a novel $\textit{Class A}$ classifier, general enough to thwart overfitting, lightweight thanks to the usage of the less costly features, and still able to correctly classify more than 95% of the accounts of the original training set. We ultimately perform an information fusion-based sensitivity analysis, to assess the global sensitivity of each of the features employed by the classifier. The findings reported in this paper, other than being supported by a thorough experimental methodology and interesting on their own, also pave the way for further investigation on the novel issue of fake Twitter followers.

Van Tien Hoang, Angelo Spognardi, Francesco Tiezzi et al.

Major search engines deploy personalized Web results to enhance users' experience, by showing them data supposed to be relevant to their interests. Even if this process may bring benefits to users while browsing, it also raises concerns on the selection of the search results. In particular, users may be unknowingly trapped by search engines in protective information bubbles, called "filter bubbles", which can have the undesired effect of separating users from information that does not fit their preferences. This paper moves from early results on quantification of personalization over Google search query results. Inspired by previous works, we have carried out some experiments consisting of search queries performed by a battery of Google accounts with differently prepared profiles. Matching query results, we quantify the level of personalization, according to topics of the queries and the profile of the accounts. This work reports initial results and it is a first step a for more extensive investigation to measure Web search personalization.