(Mis)Information Dissemination in WhatsApp: Gathering, Analyzing and Countermeasures Gustavo Resende Universidade Federal de Minas Gerais, Computer Science Department, Brazil gustavo.jota@dcc.ufmg.br Philipe Melo Universidade Federal de Minas Gerais, Computer Science Department, Brazil philipe@dcc.ufmg.br Hugo Sousa Universidade Federal de Minas Gerais, Computer Science Department, Brazil hugosousa@dcc.ufmg.br Johnnatan Messias Max Planck Institute for Software Systems (MPI-SWS), Germany johnme@mpi-sws.org Marisa Vasconcelos IBM Research marisaav@br.ibm.com Jussara M. Almeida Universidade Federal de Minas Gerais, Computer Science Department, Brazil jussara@dcc.ufmg.br Fabrício Benevenuto Universidade Federal de Minas Gerais, Computer Science Department, Brazil fabricio@dcc.ufmg.br ABSTRACT WhatsApp has revolutionized the way people communicate and interact. It is not only cheaper than the traditional Short Message Service (SMS) communication but it also brings a new form of mo- bile communication: the group chats. Such groups are great forums for collective discussions on a variety of topics. In particular, in events of great social mobilization, such as strikes and electoral campaigns, WhatsApp group chats are very attractive as they fa- cilitate information exchange among interested people. Yet, recent events have raised concerns about the spreading of misinformation in WhatsApp. In this work, we analyze information dissemination within WhatsApp, focusing on publicly accessible political-oriented groups, collecting all shared messages during major social events in Brazil: a national truck drivers’ strike and the Brazilian presi- dential campaign. We analyze the types of content shared within such groups as well as the network structures that emerge from user interactions within and cross-groups. We then deepen our analysis by identifying the presence of misinformation among the shared images using labels provided by journalists and by a pro- posed automatic procedure based on Google searches. We identify the most important sources of the fake images and analyze how they propagate across WhatsApp groups and from/to other Web platforms. CCS CONCEPTS · Networks → Online social networks; · Mathematics of com- puting → Network fows; · Information systems → Mobile in- formation processing systems; Chat . This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution. WWW ’19, May 13ś17, 2019, San Francisco, CA, USA © 2019 IW3C2 (International World Wide Web Conference Committee), published under Creative Commons CC-BY 4.0 License. ACM ISBN 978-1-4503-6674-8/19/05. https://doi.org/10.1145/3308558.3313688 KEYWORDS WhatsApp groups, misinformation, information dissemination, so- cial network structure, fake images ACM Reference Format: Gustavo Resende, Philipe Melo, Hugo Sousa, Johnnatan Messias, Marisa Vas- concelos, Jussara M. Almeida, and Fabrício Benevenuto. 2019. (Mis)Information Dissemination in WhatsApp: Gathering, Analyzing and Countermeasures. In Proceedings of the 2019 World Wide Web Conference (WWW ’19), May 13ś17, 2019, San Francisco, CA, USA. ACM, New York, NY, USA, 11 pages. https://doi.org/10.1145/3308558.3313688 1 INTRODUCTION WhatsApp is a world-wide popular messaging app with more than 1.5 billion active users [2] which is currently the main messaging app in many countries, including India, Brazil, and Germany. Nearly everyone with a smartphone uses WhatsApp in Brazil (about 120 million active users [15]) to keep in touch with friends and family, do business, as well as read the news. There are key features in WhatsApp that make this app unique. First, any communication within the app is end-to-end encrypted, meaning that messages, photos, videos, voice messages, documents, status updates, and calls are only seen by those involved in the communication. Second, WhatsApp allows users to easily create and organize chat groups. These groups, which are limited to 256 members, are by default private, as group administrators decide who can join them. However, a group manager may choose to share the link to join it in websites or social networks. In such a case, anyone with access to the link can join the group, which becomes, from a practical perspective, publicly accessible. Finally, WhatsApp provides features for viral spreading, allowing users to broadcast an initial message to 256 contacts or groups or forward content to 20 contacts or groups 1 . 1 The message forwarding was limited to 5 groups in India and 20 in the rest of the world along the period this work was developed. Currently, the limit has been updated to 5 worldwide. 818