A5075696763- Misinformation and Its Impacts
- Sentiment Analysis and Opinion Mining
- Media Influence and Health
- Indoor and Outdoor Localization Technologies
- Speech and Audio Processing
- Face recognition and analysis
- Hate Speech and Cyberbullying Detection
- Advanced Text Analysis Techniques
- Drilling and Well Engineering
- Mental Health via Writing
- Emotion and Mood Recognition
- Oil and Gas Production Techniques
- Reservoir Engineering and Simulation Methods
Centro de Estudos e Sistemas Avançados do Recife
2023-2024
Universidade de São Paulo
2022-2023
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 public, discouraging them from following the which, turn, can limit effectiveness of media. To understand people's emotional response to we have investigated prevalence basic human around 19 million user responses 1.7 news posts Twitter (English-speaking) media across 12 countries January 2020 April 2021. We used Latent Dirichlet Allocation...
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 natural language processing large-scale Twitter data to explore this in depth, identifying emotions news content user reactions it, how these evolved over course pandemic. focused major UK channels, constructing a dataset COVID-related tweets (tweets from organisations) comments response these, covering Jan 2020 April 2021. Natural...
Abstract In recent years, artificial intelligence (AI) has been changing the way industry operates, especially oil industry. exploration and production activity, specifically in Reservoirs Wells areas, use of AI growing exponentially, with applications ranging from reservoir drainage plan evaluation (CARDOSO et al., 2017) to predicting well instability issues during drilling (LENWOUE 2023). The Selection Alternatives via Artificial Intelligence – SAVIA, arises Internal Startups Program, an...
The media has been used to disseminate public information amid the Covid-19 pandemic. However, news triggered emotional responses in people that have impacted their mental well-being and led avoidance. To understand response news, we study user comments on published Twitter by 37 outlets 11 countries from Jan 2020 Dec 2022. We employ a deep-learning-based model identify one of 6 Ekman’s basic emotions, or absence expression, an implementation Latent Dirichlet Allocation (LDA) 12 different...
Lip segmentation is crucial in computer vision, especially for lip reading. Despite extensive face research, has received limited attention. The aim of this study to compare state-of-the-art models using a standardized setting and publicly available dataset. Five techniques, namely EHANet, Mask2Former, BiSeNet V2, PIDNet, STDC1, are qualitatively selected based on their reported performance, inference time, code availability, recency, popularity. CelebAMask-HQ dataset, comprising manually...
Lip segmentation is crucial in computer vision, especially for lip reading. Despite extensive face research, has received limited attention. The aim of this study to compare state-of-the-art models using a standardized setting and publicly available dataset. Five techniques, namely EHANet, Mask2Former, BiSeNet V2, PIDNet, STDCI, are qualitatively selected based on their reported performance, inference time, code availability, recency, popularity. CelebAMask-HQ dataset, comprising manually...