2,527 Hits in 1.8 sec

"Manipulation and abuse on social media" by Emilio Ferrara with Ching-man Au Yeung as coordinator

Emilio Ferrara
2015 ACM SIGWEB Newsletter  
The computer science research community has became increasingly interested in the study of social media due to their pervasiveness in the everyday life of millions of individuals. Methodological questions and technical challenges abound as more and more data from social platforms become available for analysis. This data deluge not only yields the unprecedented opportunity to unravel questions about online individuals' behavior at scale, but also allows to explore the potential perils that the
more » ... ssive adoption of social media brings to our society. These communication channels provide plenty of incentives (both economical and social) and opportunities for abuse. As social media activity became increasingly intertwined with the events in the offline world, individuals and organizations have found ways to exploit these platforms to spread misinformation, to attack and smear others, or to deceive and manipulate. During crises, social media have been effectively used for emergency response, but fear-mongering actions have also triggered mass hysteria and panic. Criminal gangs and terrorist organizations like ISIS adopt social media for propaganda and recruitment. Synthetic activity and social bots have been used to coordinate orchestrated astroturf campaigns, to manipulate political elections and the stock market. The lack of effective content verification systems on many of these platforms, including Twitter and Facebook, rises concerns when younger users become exposed to cyber-bulling, harassment, or hate speech, inducing risks like depression and suicide. This article illustrates some of the recent advances facing these issues and discusses what it remains to be done, including the challenges to address in the future to make social media a more useful and accessible, safer and healthier environment for all users.
doi:10.1145/2749279.2749283 fatcat:zmyfq5vw2zaclmjrnzjnp7lrge

Design of Automatically Adaptable Web Wrappers [article]

Emilio Ferrara, Robert Baumgartner
2011 arXiv   pre-print
Several improvements to this technique have been suggested: Ferrara and Baumgartner (Ferrara and Baumgartner, 2011) , extending the concept of weights introduced by Yang (Yang, 1991) , developed a variant  ...  (Laender et al., 2002) presented a taxonomy of wrapper generation methodologies, while Ferrara et al.  ... 
arXiv:1103.1254v1 fatcat:s2xbyq73lvecrfdrcea2ljehpe

Bots, elections, and social media: a brief overview [article]

Emilio Ferrara
2019 arXiv   pre-print
Bots, software-controlled accounts that operate on social media, have been used to manipulate and deceive. We studied the characteristics and activity of bots around major political events, including elections in various countries. In this chapter, we summarize our findings of bot operations in the context of the 2016 and 2018 US Presidential and Midterm elections and the 2017 French Presidential election.
arXiv:1910.01720v1 fatcat:6liypsz5xbhjhez27mydhyp2ti

RAPTOR: Ransomware Attack PredicTOR [article]

Florian Quinkert, Thorsten Holz, KSM Tozammel Hossain, Emilio Ferrara,, Kristina Lerman
2018 arXiv   pre-print
Ransomware, a type of malicious software that encrypts a victim's files and only releases the cryptographic key once a ransom is paid, has emerged as a potentially devastating class of cybercrimes in the past few years. In this paper, we present RAPTOR, a promising line of defense against ransomware attacks. RAPTOR fingerprints attackers' operations to forecast ransomware activity. More specifically, our method learns features of malicious domains by looking at examples of domains involved in
more » ... own ransomware attacks, and then monitors newly registered domains to identify potentially malicious ones. In addition, RAPTOR uses time series forecasting techniques to learn models of historical ransomware activity and then leverages malicious domain registrations as an external signal to forecast future ransomware activity. We illustrate RAPTOR's effectiveness by forecasting all activity stages of Cerber, a popular ransomware family. By monitoring zone files of the top-level domain .top starting from August 30, 2016 through May 31, 2017, RAPTOR predicted 2,126 newly registered domains to be potential Cerber domains. Of these, 378 later actually appeared in blacklists. Our empirical evaluation results show that using predicted domain registrations helped improve forecasts of future Cerber activity. Most importantly, our approach demonstrates the value of fusing different signals in forecasting applications in the cyber domain.
arXiv:1803.01598v1 fatcat:m7biniuejrcvvfkzasgzyajtoi

Word Embedding for Social Sciences: An Interdisciplinary Survey [article]

Akira Matsui, Emilio Ferrara
2022 arXiv   pre-print
To extract essential information from complex data, computer scientists have been developing machine learning models that learn low-dimensional representation mode. From such advances in machine learning research, not only computer scientists but also social scientists have benefited and advanced their research because human behavior or social phenomena lies in complex data. To document this emerging trend, we survey the recent studies that apply word embedding techniques to human behavior
more » ... g, building a taxonomy to illustrate the methods and procedures used in the surveyed papers and highlight the recent emerging trends applying word embedding models to non-textual human behavior data. This survey conducts a simple experiment to warn that common similarity measurements used in the literature could yield different results even if they return consistent results at an aggregate level.
arXiv:2207.03086v1 fatcat:de3rijvztfa6bg7xqstlumjkeu

Who Falls for Online Political Manipulation? [article]

Adam Badawy and Kristina Lerman and Emilio Ferrara
2018 arXiv   pre-print
The spread of misinformation [Shorey and Howard 2016; Tucker et al. 2017 ] and the increasing role of bots [Bessi and Ferrara 2016] in the 2016 US presidential elections has increased the interest in  ...  Russianaffiliated accounts were also reported in the 2017 French presidential elections, where bots were detected during the so-called MacronLeaks disinformation campaign [Ferrara 2017 ].  ... 
arXiv:1808.03281v1 fatcat:4vjdse3jdjcjvmswjfurq35suu

Predictability limit of partially observed systems [article]

Andrés Abeliuk, Zhishen Huang, Emilio Ferrara, Kristina Lerman
2020 arXiv   pre-print
Applications from finance to epidemiology and cyber-security require accurate forecasts of dynamic phenomena, which are often only partially observed. We demonstrate that a system's predictability degrades as a function of temporal sampling, regardless of the adopted forecasting model. We quantify the loss of predictability due to sampling, and show that it cannot be recovered by using external signals. We validate the generality of our theoretical findings in real-world partially observed
more » ... ms representing infectious disease outbreaks, online discussions, and software development projects. On a variety of prediction tasks---forecasting new infections, the popularity of topics in online discussions, or interest in cryptocurrency projects---predictability irrecoverably decays as a function of sampling, unveiling fundamental predictability limits in partially observed systems.
arXiv:2001.06547v1 fatcat:usfdm2lysfhc5fznr2uq74r5oa

Graph Signal Recovery Using Restricted Boltzmann Machines [article]

Ankith Mohan, Aiichiro Nakano, Emilio Ferrara
2020 arXiv   pre-print
We propose a model-agnostic pipeline to recover graph signals from an expert system by exploiting the content addressable memory property of restricted Boltzmann machine and the representational ability of a neural network. The proposed pipeline requires the deep neural network that is trained on a downward machine learning task with clean data, data which is free from any form of corruption or incompletion. We show that denoising the representations learned by the deep neural networks is
more » ... y more effective than denoising the data itself. Although this pipeline can deal with noise in any dataset, it is particularly effective for graph-structured datasets.
arXiv:2011.10549v1 fatcat:dqt52dllhnbqdggmsfrgojk22u

Deep Neural Networks for Optimal Team Composition [article]

Anna Sapienza, Palash Goyal, Emilio Ferrara
2018 arXiv   pre-print
Cooperation is a fundamental social mechanism, whose effects on human performance have been investigated in several environments. Online games are modern-days natural settings in which cooperation strongly affects human behavior. Every day, millions of players connect and play together in team-based games: the patterns of cooperation can either foster or hinder individual skill learning and performance. This work has three goals: (i) identifying teammates' influence on players' performance in
more » ... e short and long term, (ii) designing a computational framework to recommend teammates to improve players' performance, and (iii) setting to demonstrate that such improvements can be predicted via deep learning. We leverage a large dataset from Dota 2, a popular Multiplayer Online Battle Arena game. We generate a directed co-play network, whose links' weights depict the effect of teammates on players' performance. Specifically, we propose a measure of network influence that captures skill transfer from player to player over time. We then use such framing to design a recommendation system to suggest new teammates based on a modified deep neural autoencoder and we demonstrate its state-of-the-art recommendation performance. We finally provide insights into skill transfer effects: our experimental results demonstrate that such dynamics can be predicted using deep neural networks.
arXiv:1805.03285v1 fatcat:y2emfjxumvc3zlx5cwi64kkp3i

Measuring Similarity in Large-scale Folksonomies [article]

Giovanni Quattrone, Emilio Ferrara, Pasquale De Meo, Licia Capra
2012 arXiv   pre-print
Social (or folksonomic) tagging has become a very popular way to describe content within Web 2.0 websites. Unlike taxonomies, which overimpose a hierarchical categorisation of content, folksonomies enable end-users to freely create and choose the categories (in this case, tags) that best describe some content. However, as tags are informally defined, continually changing, and ungoverned, social tagging has often been criticised for lowering, rather than increasing, the efficiency of searching,
more » ... ue to the number of synonyms, homonyms, polysemy, as well as the heterogeneity of users and the noise they introduce. To address this issue, a variety of approaches have been proposed that recommend users what tags to use, both when labelling and when looking for resources. As we illustrate in this paper, real world folksonomies are characterized by power law distributions of tags, over which commonly used similarity metrics, including the Jaccard coefficient and the cosine similarity, fail to compute. We thus propose a novel metric, specifically developed to capture similarity in large-scale folksonomies, that is based on a mutual reinforcement principle: that is, two tags are deemed similar if they have been associated to similar resources, and vice-versa two resources are deemed similar if they have been labelled by similar tags. We offer an efficient realisation of this similarity metric, and assess its quality experimentally, by comparing it against cosine similarity, on three large-scale datasets, namely Bibsonomy, MovieLens and CiteULike.
arXiv:1207.6037v1 fatcat:vlt7wk4tbzfydkd3yz2qvelq2u

Characterizing the 2016 Russian IRA Influence Campaign [article]

Adam Badawy, Aseel Addawood, Kristina Lerman, Emilio Ferrara
2018 arXiv   pre-print
(2018); Ferrara et al.  ...  These effects are documented by several studies Bessi and Ferrara (2016) ; Conover et al. (2011a) ; El-Khalili (2013); Ferrara (2017); Fourney et al. (2017) ; Ratkiewicz et al. (2011a) ; Shorey and  ... 
arXiv:1812.01997v1 fatcat:4cvg4utmiffkveqkvqln7nhxxu

Modeling "Newsworthiness" for Lead-Generation Across Corpora [article]

Alexander Spangher, Nanyun Peng, Jonathan May, Emilio Ferrara
2021 arXiv   pre-print
. , , Alexander Spangher Nanyun Peng Jonathan May Emilio Ferrara Information Sciences Institute / University of Southern California {spangher, peng, jonmay, ferrarae}  ... 
arXiv:2104.09653v1 fatcat:7fsmkudn2fdrziwnwbkwruvsqa

Uncovering Criminal Behavior with Computational Tools [chapter]

Emilio Ferrara, Salvatore Catanese, Giacomo Fiumara
2015 Social Phenomena  
In this chapter we explore the opportunities brought in by advanced social network analysis techniques to study criminal behaviors and dynamics in heterogeneous communication media, along multiple dimensions including the temporal and spatial ones. To this aim, we present LogViewer, a Web framework we developed to allow network analysts to study combinations of geo-embedded and time-varying data sources like mobile phone networks and social graphs. We present some usecases inspired by
more » ... criminal investigations where we used LogViewer to study criminal networks reconstructed from mobile phone and social interactions to identify criminal behaviors and uncover illicit activities.
doi:10.1007/978-3-319-14011-7_10 fatcat:gqaxvkorejfuxikh4tzd6ffzhi

Collective behaviors and networks

Giovanni Luca Ciampaglia, Emilio Ferrara, Alessandro Flammini
2014 EPJ Data Science  
The goal of this thematic series is to provide a discussion venue about recent advances in the study of networks and their applications to the study of collective behavior in socio-technical systems. The series includes contributions exploring the intersection between data-driven studies of complex networks and agent-based models of collective social behavior. Particular attention is devoted to topics aimed at understanding social behavior through the lens of data about technology-mediated
more » ... nication. These include: modeling social dynamics of attention and collaboration, characterizing online group formation and evolution, and studying the emergence of roles and interaction patterns in social media environments.
doi:10.1140/epjds/s13688-014-0037-6 fatcat:ksmjbdi3q5czdcjs4rathvh6fy

Measuring Bot and Human Behavioral Dynamics

Iacopo Pozzana, Emilio Ferrara
2020 Frontiers in Physics  
Emilio Ferrara ( FIGURE 1 | 1 Frequency distribution of the bot scores obtained with Botometer.  ...  In Ferrara et al.  ...  Copyright © 2020 Pozzana and Ferrara. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY).  ... 
doi:10.3389/fphy.2020.00125 fatcat:ured25oggbg27dcmtlacpzvypa
« Previous Showing results 1 — 15 out of 2,527 results