5th International Workshop on Mining Actionable Insights from Social Networks

Special Edition on Dis/Misinformation Mining from Social Media


Talk: Deploying Real Systems to Counter Misinformation Campaigns

Abstract. The political debate and electoral dispute in the online space have been marked by an information war in many recent elections. In order to mitigate the misinformation problem, we developed technological solutions able to reduce the abuse of misinformation campaigns in the online space and we deployed it along the 2018 Brazilian elections. Particularly, we created a system to monitor public groups in WhatsApp and a system to monitor Ads in Facebook, bringing some transparency for the campaigns on these online spaces. Our systems showed to be fundamental for fact-checking and investigative journalism, currently being used by various fact-checking agencies.

Bio. Fabrício Benevenuto is associate professor in the Computer Science Department of Federal University at Minas Gerais (UFMG) and a former member of the Brazilian Academy of Science (2013-2017). In 2017 he received a Humboldt fellowship through which he was a visiting faculty at Max Planck Institute. He is author of awarded papers, including the test-of-time award from ICWSM and a best nominee at WWW, both received in 2020. Currently, he leads a series of projects towards understanding, measuring, and countering misinformation campaigns in social networks. His work on these topics has led to a large number of relevant publications, widely cited papers, and systems with real world impact.

Talk: AI & Social Manipulation

Abstract. Networks have dramatically changed the way we experience the world. Information access and broadcasting have been revolutionized. The Internet, the Web, and online platforms bring us together: our society is experiencing the effects, both positive and negative, of ubiquitous and unparalleled connectivity. In this talk, I will overview my decade-long journey into understanding the implications of online platforms for our society, democracy, and public health. I'll first focus on online misinformation as an endemic phenomenon in social media, and illustrate how bots and trolls exacerbate the spread of inaccurate information. Their operations span domains from politics to public health. I'll dive deep into our discovery that bots attempted to manipulate the online conversation about the 2016 US Election. Our work is the only peer-reviewed study of online political interference appeared before November 8, 2016, and it has informed official government investigations as well as new policies and regulations. I'll also overview how conspiracy theories about vaccines, epidemic outbreaks, and other health-related rumours can have adverse effects and contribute toward public health crises. I'll conclude by discussing the tools we developed to understand and combat online misinformation, detect bots and trolls, and characterize their activity, behaviour, and strategies, suggesting how they are changing the way researchers and the public study communication networks in the era of automation and artificial intelligence.

Bio. Dr. Emilio Ferrara is Research Assistant Professor and Associate Director of Informatics & Data Science at the USC Department of Computer Science, Research Team Leader at the USC Information Sciences Institute, and Principal Investigator at the USC/ISI Machine Intelligence and Data Science (MINDS) group. Ferrara's research interests include using AI for modeling and predicting human behavior in techno-social systems. Ferrara has published over a hundred articles on social networks, machine learning, and network science, appeared in venues like Proceeding of the National Academy of Sciences, Communications of the ACM, Physical Review Letters, and his research has been featured on all major news outlets. He was named 2015 IBM Watson Big Data Influencer, he received the 2016 DARPA Young Faculty Award, the 2016 Complex Systems Society Junior Scientific Award, and the 2018 DARPA Director's Fellowship. His research is supported by DARPA, IARPA, Air Force, and Office of Naval Research. He is Associate Editor of EPJ Data Science, Plos One, and on the Editorial Board of Future Internet and Data Science. He was Founding Editor of Future Internet: Techno-Social Smart Systems.

Talk: The Emotional Characteristics of Social Media and Political Misperceptions

Abstract. Society’s turn to social media as a primary source of news and political information means that the democratic ideal of an accurately informed public is now challenged by user-created and shared content that is misleading, inaccurate, or blatantly false. In this talk I argue that emotions exacerbate the problem and make it more likely that people are exposed to false information, share it, and believe it. First, I illustrate how emotions bias what news and information people seek and are exposed to in social media, including misinformation. Second, I describe the various ways in which emotions affect how people engage news in social media, including sharing, and its consequences for false beliefs. Finally, I demonstrate how the emotional character of social media can lead to inaccurate political beliefs.

Bio. Brian Weeks is an Assistant Professor in the Department of Communication and Media and a Faculty Associate in the Center for Political Studies at the University of Michigan. His research focuses on two general topics: (1) how individuals are exposed to, engage with, evaluate, and learn from news and socially shared political information in digital media; and (2) the influence of political misinformation on beliefs and the effects of corrective messages. Weeks’s published research appears in leading journals in the field of communication including the Journal of Communication, Journal of Computer-Mediated Communication, Human Communication Research, New Media & Society, Communication Research, and elsewhere. At Michigan he co-founded the Politics and Communication Lab (PAC LAB) and is a core member of the Political Communication Working Group. Weeks received a Ph.D. in communication from the Ohio State University and prior to joining the University of Michigan he was a faculty member at the University of Vienna in Austria.

Talk: Fake News Research: Challenges and New Directions

Abstract. Fake news is now viewed as one of the greatest threats to democracy, journalism, and freedom of expression. It has weakened public trust in governments and its potential impact on the contentious "Brexit'' referendum and the equally divisive 2016 U.S. presidential election -- which it might have affected -- is yet to be realized. The talk will briefly review some of the modern fake news detection techniques, along with some of the current challenges. We will discuss some recent advancements to tackle these challenges, with particular focus on fake news early detection and multi-modal fake news analysis.

Bio. Reza Zafarani is an Assistant Professor of electrical engineering and computer science at Syracuse University. His research interests are in Data Mining, Machine Learning, Social Media Mining, and Social Network Analysis. His research has been published at major academic venues, and highlighted in various scientific and news outlets. He is the principal author of "Social Media Mining: An Introduction", a textbook by Cambridge University Press and the associate editor for SIGKDD Explorations and Frontiers in communication. He is the winner of the NSF CAREER award, President’s Award for Innovation, and outstanding teaching award at Arizona State University.