Francisco Braulio Oliveira

Francisco Braulio Oliveira

Auto-generated profile, based on publicly available information

Francisco Braulio Oliveira

Universidade de São Paulo (USP)

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
9 February 2022 in IEEE Access
Verified
Journal Article
Open access
FOFrancisco Braulio Oliveira
Francisco Braulio Oliveira
AHAmanul Haque
Amanul Haque
DMDavoud Mougouei
Davoud Mougouei
SESimon Evans
Simon Evans
JSJaime Simão Sichman
Jaime Simão Sichman
MSMunindar P. Singh
Munindar P. Singh
Media has played an important role in public information on COVID-19. But distressing news, e.g., COVID-19 death tolls, may trigger negative emotions in public, discouraging them from following the news, which, in turn, can limit the effectiveness of the media. To understand people’s emotional response to the COVID-19 news, we have investigated the prevalence of basic human emotions in around 19 million user responses to 1.7 million COVID-19 news posts on Twitter from (English-speaking) media across 12 countries from January 2020 to April 2021. We have used Latent Dirichlet Allocation (LDA) to identify news themes on Twitter. Also, the Robustly Optimized BERT Pretraining Approach (RoBERTa) model was used to identify emotions in the tweets. Our analysis of the Twitter data revealed that anger was the most prevalent emotion in user responses to the news coverage of COVID-19. That was followed by sadness, optimism, and joy, steadily over the period of the study. The prevalence of anger (in user responses) was higher for the news about authorities and politics while optimism and joy were more prevalent for the news about vaccination and educational impacts of COVID-19 respectively. The prevalence of sadness in user responses, however, was the highest for the news about COVID-19 cases and deaths and the impacts on the families, mental health, jails, and nursing homes. We also observed a higher level of anger in the user responses to the (COVID-19) news posted by the USA media accounts (e.g., CNN Politics, Fox News, MSNBC). Optimism, on the other hand, was found to be the highest for Filipino media accounts.

9 March 2023 in Human Behavior and Emerging Technologies
Verified
Journal Article
Open access
PDF file
SESimon Evans
Simon Evans
RJRosalind Jones
Rosalind Jones
EAErkan Alkan
Erkan Alkan
JSJaime Simão Sichman
Jaime Simão Sichman
AHAmanul Haque
Amanul Haque
DMDavoud Mougouei
Davoud Mougouei
The emotional impact of the COVID-19 pandemic and ensuing social restrictions has been profound, with widespread negative effects on mental health. We made use of the natural language processing and large-scale Twitter data to explore this in depth, identifying emotions in COVID-19 news content and user reactions to it, and how these evolved over the course of the pandemic. We focused on major UK news channels, constructing a dataset of COVID-related news tweets (tweets from news organisations) and user comments made in response to these, covering Jan 2020 to April 2021. Natural language processing was used to analyse topics and levels of anger, joy, optimism, and sadness. Overall, sadness was the most prevalent emotion in the news tweets, but this was seen to decline over the timeframe under study. In contrast, amongst user tweets, anger was the overall most prevalent emotion. Time epochs were defined according to the time course of the UK social restrictions, and some interesting effects emerged regarding these. Further, correlation analysis revealed significant positive correlations between the emotions in the news tweets and the emotions expressed amongst the user tweets made in response, across all channels studied. Results provide unique insight onto how the dominant emotions present in UK news and user tweets evolved as the pandemic unfolded. Correspondence between news and user tweet emotional content highlights the potential emotional effect of online news on users and points to strategies to combat the negative mental health impact of the pandemic.

15 June 2023 in Online Social Networks and Media
Verified
Journal Article
Closed access
FOFrancisco Bráulio Oliveira
Francisco Bráulio Oliveira
DMDavoud Mougouei
Davoud Mougouei
AHAmanul Haque
Amanul Haque
JSJaime Simão Sichman
Jaime Simão Sichman
HDHoa Khanh Dam
Hoa Khanh Dam
MSMunindar P. Singh
Munindar P. Singh

29 October 2023
Verified
Conference Paper
Open access
PMPietro B. S. Masur
Pietro B. S. Masur
FOFrancisco Braulio Oliveira
Francisco Braulio Oliveira
LMLucas Moreira Medino
Lucas Moreira Medino
EHEmanuel Huber
Emanuel Huber
MPMilene Haraguchi Padilha
Milene Haraguchi Padilha
RSRenata Sellaro
Renata Sellaro
Lip segmentation is crucial in computer vision, especially for lip reading. Despite extensive face segmentation research, lip segmentation has received limited attention. The aim of this study is to compare state-of-the-art lip segmentation models using a standardized setting and a publicly available dataset. Five techniques, namely EHANet, Mask2Former, BiSeNet V2, PIDNet, and STDCI, are qualitatively selected based on their reported performance, inference time, code availability, recency, and popularity. The CelebAMask-HQ dataset, comprising manually annotated face images, is used to fairly assess the lip segmentation performance of the selected models. Inference experiments are conducted on a Raspberry Pi4 to emulate limited computational resources. The results show that Mask2Former and EHANet have the best performances in terms of mIoU score. BiSeNet V2 demonstrate competitive performance, while PIDNet excels in recall but has lower precision. Most models present inference time ranging from 1000 to around 3000 milliseconds on a Raspberry Pi4, with PIDNet having the lowest mean inference time. This study provides a comprehensive evaluation of lip segmentation models, highlighting their performance and inference times. The findings contribute to the development of lightweight techniques and establish benchmarks for future advances in lip segmentation, especially in IoT and edge computing scenarios.