Millions of social bots invaded Twitter!

Blog
Our work titled Online Human-Bot Interactions: Detection, Estimation, and Characterization has been accepted for publication at the prestigious International AAAI Conference on Web and Social Media (ICWSM 2017) to be held in Montreal, Canada in May 2017! The goal of this study was twofold: first, we aimed at understanding how difficult is to detect social bots on Twitter respectively for machine learning models and for humans. Second, we wanted to perform a census of the Twitter population to estimate how many accounts are not controlled by humans, but rather by computer software (bots). To address the first question, we developed a family of machine learning models that leverages over one thousand features characterising the online behaviour of Twitter accounts. We then trained these models with manually-annotated collections of examples of…
Read More

Complex System Society 2016 Junior Scientific Award!

Blog
I was selected as recipient of the 2016 Junior Scientific Award by the Complex System Society! The award reads: Emilio Ferrara is one of the most active and successful young researchers in the field of computational social sciences. His works include the design and application of novel network-science models, algorithms, and tools to study phenomena occurring in large, dynamical techno-social systems. They improved our understanding of the structure of large online social networks and the dynamics of information diffusion. He has explored online social phenomena (protests, rumours, etc.), with applications to model and forecast individual behaviour, and characterise information diffusion and cyber-crime. 
Read More

Twitter, Social Bots, and the US Presidential Elections!

Blog
Our paper titled Social bots distort the 2016 U.S. Presidential election online discussion was published on the November 2016 issue of First Monday and selected as Editor's featured article! We investigated how social bots, automatic accounts that populate the Twitter-sphere, are distorting the online discussion about the 2016 U.S. Presidential elections. In a nutshell, we discovered that: About one-in-five tweets regarding the elections has been posted by a bot, totalling about 4 Million tweets posted during the month prior to the elections by over 400,000 bots. Regular (human) users cannot determine whether the source of some specific information is another legitimate user or a bot: therefore, bots are being retweeted at the same rate as humans. Bots are biased (by construction): Trump-supporting bots, for example, are producing systematically only positive contents in support of…
Read More

The Rise of Social Bots!

Blog
Emilio Ferrara discusses "The Rise of Social Bots" on the July 2016 Communications of the ACM. Our review paper on the rise of social bots has appeared on the cover of the July 2016 issue of Communications of the ACM and is the subject of my interview above! Social bots populate techno-social systems: they are often benign, or even useful, but some are created to harm, by tampering with, manipulating, and deceiving social media users. Social bots have been used to infiltrate political discourse, manipulate the stock market, steal personal information, and spread misinformation. The detection of social bots is therefore an important research endeavor. A taxonomy of the different social bot detection systems proposed in the literature accounts for network-based techniques, crowdsourcing strategies, feature-based supervised learning, and hybrid systems.…
Read More

The structure of Mafia syndacates

Blog
S Agreste, S Catanese, P De Meo, E Ferrara, G Fiumara. Network structure and resilience of Mafia syndicates. Information Sciences, 2016 Useful links: Journal page | Arxiv In this paper in collaboration with colleagues from University of Messina (Italy) we present the results of our study of Sicilian Mafia organizations using social network analysis. The study investigates the network structure of a Mafia syndicate, describing its evolution and highlighting its plasticity to membership-targeting interventions and its resilience to disruption caused by police operations. We analyze two different datasets dealing with Mafia gangs that were built by examining different digital trails and judicial documents that span a period of ten years. The first dataset includes the phone contacts among suspected individuals, and the second captures the relationships among individuals actively involved in various…
Read More

Emotional contagion in Twitter!

Blog
E Ferrara, Z Yang. Measuring Emotional Contagion in Social Media. PLoS ONE, 2015 Useful links: Journal page Spotlight: How Emotions Spread On Twitter from USC Viterbi on Vimeo. Our recent work on measuring the presence of emotional contagion in Twitter is finally published on Plos One! The paper, in collaboration with Zeyao (Patrick) Yang who recently graduated from Indiana University, is attracting a lot of media attention! The theory of emotional contagion hypothesizes that emotions and emotional states are transferred from one person to another by social interactions. Traditional social science studies that date more than half a century ago' (Fromm, The Art of Loving, 1956) aimed at proving that in-person exchanges cause the unconscious emotional alignment of the interacting parties. One hypothesis was that non-verbal cues (body language, facial expressions, tone of the voice, etc.)…
Read More

Style in the age of Instagram!

Blog
J Park, GL Ciampaglia, and E Ferrara. The 19th ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW 2016) Useful links: Arxiv | ACM Our work on Science of Success applied to the Fashion world is attracting a lot of media attention! The paper, in collaboration with IU PhD student Jaehyuk Park and my colleague and friend IU Research Scientist Giovanni Luca Ciampaglia, will be presented at CSCW 2016! We introduce a new machine learning framework, rooted in a through statistical analysis of a combination of physical attributes, professional information, and social media (Instagram) data, that is able to predict the rise to popularity of new fashion models with over 80% accuracy! To test the forecasting ability of our system we actually predicted the success of 6 out 7 new…
Read More

Defining and identifying Sleeping Beauties in science

Blog
Q Ke, E Ferrara, F Radicchi, and A Flammini. Proceedings of the National Academy of Sciences, 2015 Useful links: Arxiv | PNAS Scientific papers typically have a finite lifetime: their rate to attract citations achieves its maximum a few years after publication, and then steadily declines. Previous studies pointed out the existence of a few blatant exceptions: papers whose relevance has not been recognized for decades, but then suddenly become highly influential and cited. The Einstein, Podolsky, and Rosen “paradox” paper is an exemplar Sleeping Beauty. We study how common Sleeping Beauties are in science. We introduce a quantity that captures both the recognition intensity and the duration of the “sleeping” period, and show that Sleeping Beauties are far from exceptional. The distribution of such quantity is continuous and has…
Read More

Evolution of Online User Behavior During a Social Upheaval

Blog
O Varol, E Ferrara, C Ogan, F Menczer, and A Flammini. ACM Web Science 2014 Useful links: Arxiv | ACM Digital Library. Social media represent powerful tools of mass communication and information diffusion. They played a pivotal role during recent social uprisings and political mobilizations across the world. Here we present a study of the Gezi Park movement in Turkey through the lens of Twitter. We analyze over 2.3 million tweets produced during the 25 days of protest occurred between May and June 2013. We first characterize the spatio-temporal nature of the conversation about the Gezi Park demonstrations, showing that similarity in trends of discussion mirrors geographic cues. We then describe the characteristics of the users involved in this conversation and what roles they played. We study how roles and…
Read More

Detecting criminal organizations in mobile phone networks

Blog
E Ferrara, S Catanese, P De Meo, and G Fiumara. Expert Systems with Applications, 4:5733-5750, (2014). Useful links: Journal Page | Arxiv | PDF. The study of criminal networks using traces from heterogeneous communication media is acquiring increasing importance in nowadays society. The usage of communication media such as phone calls and online social networks leaves digital traces in the form of metadata that can be used for this type of analysis. The goal of this work is twofold: first we provide a theoretical framework for the problem of detecting and characterizing criminal organizations in networks reconstructed from phone call records. Then, we introduce an expert system to support law enforcement agencies in the task of unveiling the underlying structure of criminal networks hidden in communication data. This platform allows…
Read More