O Paradoxo da Viralização de Informação Criptografada no WhatsApp

WhatsApp is a mobile communication system that allows people to interact through groups. In this work, we analyze the dissemination of information within a group network that simulates the WhatsApp network. The built network considers two types of groups: organic groups, formed by friends and family, and artificial groups that are usually created with the purpose of being a mean of spreading certain subject or event, such as political campaigns. We analyzed the speed with which information is spread in this network considering the epidemiological model Susceptible-Infected (SI). We then deepen our analysis in order to identify parameters that cause this scattering to be partially controlled in order to make it difficult to propagate fake news in these networks. Our results quantify the viralization ability of content in WhatsApp and identify aspects that could limit such ability to prevent the platform from being abused in election periods.

[1]  Karthik Bhat,et al.  WhatsApp for Monitoring and Response during Critical Events: Aggie in the Ghana 2016 Election , 2017, ISCRAM.

[2]  Yaron Ariel,et al.  Fighting, worrying and sharing: Operation ‘Protective Edge’ as the first WhatsApp war , 2015 .

[3]  Fabrício Benevenuto,et al.  A Measurement Study of Hate Speech in Social Media , 2017, HT.

[4]  M. Keeling,et al.  Networks and epidemic models , 2005, Journal of The Royal Society Interface.

[5]  Fabrício Benevenuto,et al.  A System for Monitoring Public Political Groups in WhatsApp , 2018, WebMedia.

[6]  Jussara M. Almeida,et al.  WhatsApp Monitor: A Fact-Checking System for WhatsApp , 2019, ICWSM.

[7]  Ling Feng,et al.  A Cluster-Based Epidemic Model for Retweeting Trend Prediction on Micro-blog , 2015, DEXA.

[8]  Emilio Ferrara,et al.  Social Bots Distort the 2016 US Presidential Election Online Discussion , 2016, First Monday.

[9]  Venkata Rama Kiran Garimella,et al.  WhatsApp, Doc? A First Look at WhatsApp Public Group Data , 2018, ICWSM 2018.

[10]  P. Howard,et al.  The Upheavals in Egypt and Tunisia: The Role of Digital Media , 2011 .

[11]  Krishna P. Gummadi,et al.  Delayed information cascades in Flickr: Measurement, analysis, and modeling , 2012, Comput. Networks.

[12]  Krishna P. Gummadi,et al.  Potential for Discrimination in Online Targeted Advertising , 2018, FAT.

[13]  Pooja Khurana,et al.  Sir Model for Fake News Spreading Through Whatsapp , 2018 .

[14]  Kate Starbird,et al.  Ecosystem or Echo-System? Exploring Content Sharing across Alternative Media Domains , 2018, ICWSM.

[15]  Johnnatan Messias,et al.  On Microtargeting Socially Divisive Ads: A Case Study of Russia-Linked Ad Campaigns on Facebook , 2018, FAT.

[16]  Fabrício Benevenuto,et al.  Reverse engineering socialbot infiltration strategies in Twitter , 2014, 2015 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[17]  Michael Seufert,et al.  Analysis of Group-Based Communication in WhatsApp , 2015, MONAMI.

[18]  Jure Leskovec,et al.  Image Labeling on a Network: Using Social-Network Metadata for Image Classification , 2012, ECCV.

[19]  Fabrício Benevenuto,et al.  Supervised Learning for Fake News Detection , 2019, IEEE Intelligent Systems.

[20]  Phuoc Tran-Gia,et al.  Group-based communication in WhatsApp , 2016, 2016 IFIP Networking Conference (IFIP Networking) and Workshops.

[21]  Sarit Kraus,et al.  A Study of WhatsApp Usage Patterns and Prediction Models without Message Content , 2018, ArXiv.

[22]  Fabrício Benevenuto,et al.  Measuring the Facebook Advertising Ecosystem , 2019, NDSS.

[23]  Ramanathan V. Guha,et al.  Propagation of trust and distrust , 2004, WWW '04.

[24]  Fabrício Benevenuto,et al.  (Mis)Information Dissemination in WhatsApp: Gathering, Analyzing and Countermeasures , 2019, WWW.