GOGabriel Pereira de Oliveira

Gabriel Pereira de Oliveira

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Gabriel Pereira de Oliveira has a total of 61 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Weak Ordinal Supervision for Causal Structure Learning from Clinical Narratives

    by Anne I. R. Carvalho, Gabriel P. Oliveira, Luis A. Duarte, Eduardo Birchal, Matheus C. Teixeira, Gustavo Jacob, Ana Paula Couto da Silva, Gisele L. Pappa, Anisio Lacerda

  • CausalGA: An Evolutionary Framework for Causal Structure Learning

    by Luis A. Duarte, Matheus C. Teixeira, Anne I. R. Carvalho, Eduardo Birchal, Lucas Albuquerque, Gabriel P. Oliveira, Gisele L. Pappa, Anisio Lacerda

  • Painel Trilhas de Licitações: Trilhas Investigativas para Geração de Alertas em Licitações de Minas Gerais

    by Lucas G. L. Costa, Gabriel P. Oliveira, Mariana O. Silva, Luciana de Cássia Silva Faria, Wagner Meira Jr., Gisele L. Pappa

    Este artigo apresenta o Painel Trilhas de Licitações, um sistema inteligente para apoio à detecção de indícios de fraude em licitações públicas no estado de Minas Gerais. A ferramenta integra múltiplas fontes de dados governamentais e utiliza trilhas investigativas para geração automática de alertas e priorização de auditorias. O sistema combina integração de dados com análise relacional para identificar conexões suspeitas entre licitantes e itens licitados, além de oferecer visualizações interativas que auxiliam auditores e promotores na investigação. Os resultados indicam potencial para aumentar a eficiência da fiscalização e fortalecer o combate à corrupção.

  • Open Access

    Epidemic wave dynamics of music virality on online social platforms

    by Gabriel P. Oliveira, Luca Vassio, Ana Paula Couto da Silva, Mirella M. Moro

    Social media and streaming platforms have reshaped music consumption, enabling songs to go viral through social contagion processes that mirror the spread of infectious diseases. In this article, we investigate whether epidemiological models can effectively represent, interpret, and forecast music virality on online platforms. We introduce a wave-based approach that captures multiple independent bursts of popularity, which is not possible using classic epidemic models. We evaluate our approach using data from Spotify and TikTok, comparing its performance with traditional time-series forecasting methods. Our findings demonstrate that epidemic models are significantly more effective at capturing viral dynamics than long-term commercial success. In forecasting tasks, our method achieves accuracy comparable to conventional techniques, even when trained on partial data, while offering interpretable parameters that characterize diffusion speed, engagement duration, and adoption delay. A cross-platform comparison reveals that viral trajectories on TikTok are captured with even greater precision than those on Spotify. Overall, our findings support epidemic modeling as a powerful and interpretable framework for analyzing and forecasting music virality in contemporary digital ecosystems.

  • Open Access

    Detecting and Analyzing Anomalies in City Expenditure Time Series

    by Marco Túlio Dutra, Lucas G. L. Costa, Gabriel P. Oliveira, Mariana O. Silva, Gisele L. Pappa

    This paper presents an enhanced approach for detecting and analyzing anomalies in public expenditure time series. The method combines statistical techniques and machine learning models to identify unusual spending behaviors and to rank expenditure items according to both the frequency of anomalies and the monetary impact involved. The statistically generated anomalies produce suspicion alerts of potential fraud, with the objective of prioritizing cases and directing human audit efforts more effectively. In this extended version, we introduce a finer-grained analysis that examines spending patterns at a more detailed level within the governmental budget structure, allowing the detection of irregularities that may not be visible under more aggregated views. The approach is validated on a real-world dataset comprising more than one million city expenditure records from the state of Minas Gerais, and the results demonstrate its ability to reveal irregularities that may remain hidden under higher levels of aggregation.

  • Open Access

    Music virality on social platforms: A literature review

    by Gabriel P. Oliveira, Ana Paula Couto da Silva, Mirella M. Moro

    Online social platforms have amplified content virality, including songs that quickly reach millions of users, making music virality a growing research topic in fields such as computing, music, communication, and marketing. Therefore, this article presents a literature review on music virality on social media to understand and summarize existing research on such a topic from a computing perspective. We provide an overview of key dimensions, including temporal evolution, perspectives on virality, links to musical success, data sources, approaches, and methods. Results highlight the central role of platforms such as YouTube and TikTok, the relationship between virality and success, and the use of both quantitative and qualitative approaches. Overall, this work can be a starting point for research focusing on music virality and its complex dynamics, as it emerges as a relevant topic with connections to the areas of social computing, music information retrieval, and marketing.

  • Open Access

    Modeling music popularity as an epidemic: insights from the Brazilian market

    by Gabriel P. Oliveira, Luca Vassio, Ana Paula Couto da Silva, Mirella M. Moro

    Social networks have drastically changed the music market scenario, enabling songs to reach massive audiences in record time. Given the fast-paced nature of music popularity, this work investigates whether epidemic models can effectively capture how songs gain traction. We apply the Susceptible-Infected-Recovered (SIR) model to analyze music virality and success in Brazil. Virality reflects a song’s rapid surge in popularity, whereas success represents its long-term endurance. By comparing the model’s fit for both trajectories, we assess its strengths and limitations in capturing music popularity trends. Our findings reveal that SIR provides a better fit for virality than for long-term success, reinforcing the differences between both processes and, consequently, offering a new perspective on how songs become popular in the digital age.


  • Open Access

    Influência Externa na Popularidade Musical: Google Trends como Indicador de Viralidade e Sucesso no Spotify

    by Gabriela A. Fonseca, Gabriel P. Oliveira, Ana Paula Couto da Silva

    O mercado musical contemporâneo, impulsionado pela ascensão das plataformas de streaming, reflete novas dinâmicas de consumo influenciadas por tendências de diferentes plataformas sociais. Para ampliar a compreensão acerca de tais fenômenos, este trabalho investiga a relação entre o interesse público, medido por buscas no Google, e a popularidade musical no Spotify, através de análises de correlação e causalidade de Granger. Os resultados mostram evidências pontuais para uma relação estatística entre ambos os fenônemos, embora não generalizáveis a todas as canções, reforçando que o desempenho musical é um fenômeno complexo e multifacetado.

  • Open Access

    On the Causal Relationship Between Music Virality and Success

    by Gabriel P. Oliveira, Ana Paula Couto Da Silva, Mirella M. Moro

    Songs going viral is not a new phenomenon in the music industry. Still, this phenomenon has reached new heights with the popularization of the Web and social platforms, which allow songs to achieve worldwide hit status almost instantly. Although interconnected, musical virality and commercial success are distinct concepts, and platforms such as TikTok have had significant power in amplifying music virality and creating successful hits. In this work, we analyze the temporal connection between musical virality and success. Specifically, our goal is to investigate the causal relationship between such concepts. By using global chart data from streaming platforms, we model time series to represent songs’ viral and success evolution over time and then perform two distinct analyses over them. First, we use Granger Causality to assess whether musical virality can forecast success and vice versa. Then we address the causal discovery task to qualitatively uncover the underlying causal relationships between them. The results suggest there is potential for using music virality to forecast future success and vice versa, although this does not apply to all songs. Despite their symbiotic relationship influenced by social platforms, our findings reinforce the contrast between music virality and success as different facets of music popularity.


  • GovBERT-BR: A BERT-Based Language Model for Brazilian Portuguese Governmental Data

    by Mariana O. Silva, Gabriel P. Oliveira, Lucas G. L. Costa, Gisele L. Pappa