SGSamuel Guimarães

Samuel Guimarães

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Samuel Guimarães has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Which Types of Brazilian Telegram Groups are More Susceptible to being Politicized?

    by Samuel Guimarães, Filipe Ribeiro, Oana Goga, Fabricio Benevenuto

    Online social networks (OSNs) serve as environments for various forms of social interaction, ranging from influencers interacting with their fans to more peer-to-peer forms of community debate. Instant messaging platforms are an example of spaces used for more horizontal peer-to-peer conversations. During election cycles, these digital spaces often become exposed to political manipulation and propaganda based on social ties. Regardless of their original purpose, politics can co-opt the group discourse in a process of politicization. Although studies explored the politicization of non-political topics such as vaccines and political coordination in OSNs, the politicization of non-political spaces themselves remains overlooked. This study investigates the politicization of non-political public Telegram groups in the context of the 2022 Brazilian elections. Using a curated set of Brazilian Telegram groups, we extract the data via the Telethon API and apply a BERT model to detect political messages. Our findings indicate a 60% increase in political content, primarily occurring in groups with themes indirectly related to politics (e.g., News) or in groups with more general-purpose themes that foster open-ended discussions (e.g., Leisure). This political content is concentrated in a few users, generating more engagement and further political debate.

  • Open Access

    FactCheckBureau: Build Your Own Fact-Check Analysis Pipeline

    by Oana Balalau, Pablo Bertaud-Velten, Younes El Fraihi, Garima Gaur, Oana Goga, Samuel Guimaraes, Ioana Manolescu, Brahim Saadi

    Fact-checkers are overwhelmed by the volume of claims they need to pay attention to fight misinformation. Even once debunked, a claim may still be spread by people unaware that it is false, or it may be recycled as a source of inspiration by malicious users. Hence, the importance of fact-check (FC) retrieval as a research problem: given a claim and a database of previous checks, find the checks relevant to the claim. Existing solutions addressing this problem rely on the strategy of retrieve and re-rank relevant documents. We have built FactCheckBureau, an end-to-end solution that enables researchers to easily and interactively design and evaluate FC retrieval pipelines. We also present a corpus we have built, which can be used in further research to test fact-check retrieval tools. The source code of our tool is available at this link.


  • Open Access

    Anatomy of Hate Speech Datasets

    by Samuel Guimarães, Gabriel Kakizaki, Philipe Melo, Márcio Silva, Fabricio Murai, Julio C. S. Reis, Fabrício Benevenuto


  • Characterizing political bias and comments associated with news on Brazilian Facebook

    by Samuel S. Guimarães, Julio C. S. Reis, Marisa Vasconcelos, Fabrício Benevenuto


  • Characterizing Reactions and Comments Associated with News on Facebook

    by Samuel Guimarães, Fabrício Benevenuto

    News consumption is increasingly done on social media websites. In this environment, all types of entities and people present themselves as news sources. These new outlets might focus on specific audiences, and some exhibit the news less objectively. Facebook is one of these platforms, which categorizes an extensive group of pages as a kind of news media. To analyze this phenomenon, it is crucial to characterize all pages that disseminate information in this ecosystem. Our main objective is to create an in-depth diagnostic of news stories and opinions, focusing on Brazilian Facebook. Our contributions are: (i) a new method to measure the political bias of Facebook pages on a given country, and (ii) a detailed characterization of a comprehensive sample of these pages.