Fighting "Fake News" Through Authorship Attribution and Phylogeny Analysis

• Grant number: 18/10204-6
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: October 01, 2018
• End date: December 31, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: Antônio Carlos Theóphilo Costa Júnior
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil
• Associated research grant: 17/12646-3 - Déjà vu: feature-space-time coherence from heterogeneous data for media integrity analytics and interpretation of events, AP.TEM
• Associated scholarship(s): 19/21030-1 - Fighting fake news through phylogeny analysis, BE.EP.DR

Abstract

The world is facing a new era in which social media communication plays a fundamental role in people's lives. Along with irrefutable benefits, several collateral drawbacks have risen, one being the wide spread of false information with malicious intents, what is now commonly called "Fake News". The fight against this problem is not easy, specially when taking into account the nature of text messages involved on social media platforms (a sea of small messages and myriad users). To address this scenario, this research project aims to solve two important and difficult problems: authorship attribution and phylogeny analysis of small text messages posted on social media platforms, showing how these solutions can help in the identification of false information spread on social networks. Differently from what has been done with longer texts, we will rely upon data-driven approaches, exploiting the recent advances of deep neural networks in the field of pattern recognition. By trying to solve an ever-growing problem of our society, this research will produce outcomes that can be used by many actors, mostly social media platforms, which can directly apply the techniques developed and bring higher reliability and also transparency to the published data. This research can also provide appropriate tools to achieve another level of understanding regarding online posts, taking into consideration their spread and power of influence.

Scientific publications

(5)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

THEOPHILO, ANTONIO; PEREIRA, LUIS A. M.; ROCHA, ANDERSON; IEEE. A NEEDLE IN A HAYSTACK? HARNESSING ONOMATOPOEIA AND USER-SPECIFIC STYLOMETRICS FOR AUTHORSHIP ATTRIBUTION OF MICRO-MESSAGES. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), v. N/A, p. 5-pg., 2019-01-01. (17/12646-3, 18/10204-6)

SCHWARZ, STEPHANE; THEOPHILO, ANTONTO; ROCHA, ANDERSON; IEEE. EMET: EMBEDDINGS FROM MULTILINGUAL-ENCODER TRANSFORMER FOR FAKE NEWS DETECTION. 2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, v. N/A, p. 5-pg., 2020-01-01. (18/10204-6, 17/12646-3)

THEOPHILO, ANTONIO; GIOT, ROMAIN; ROCHA, ANDERSON. Authorship Attribution of Social Media Messages. IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS, NOV 2021. (18/10204-6, 17/12646-3)

BERTOCCO, GABRIEL; THEOPHILO, ANTONIO; ANDALO, FERNANDA; ROCHA, ANDERSON. Leveraging Ensembles and Self-Supervised Learning for Fully-Unsupervised Person Re-Identification and Text Authorship Attribution. IEEE Transactions on Information Forensics and Security, v. 18, p. 15-pg., 2023-01-01. (19/15825-1, 18/10204-6, 17/12646-3)

THEOPHILO, ANTONIO; PADILHA, RAFAEL; ANDALO, FERNANDA A.; ROCHA, ANDERSON; IEEE. EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR AUTHORSHIP ATTRIBUTION ON SOCIAL MEDIA. 2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), v. N/A, p. 5-pg., 2022-01-01. (17/12646-3, 18/10204-6, 17/21957-2)