A5087505547- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems
- Text Readability and Simplification
- Sentiment Analysis and Opinion Mining
- Advanced Text Analysis Techniques
- Semantic Web and Ontologies
- Biomedical Text Mining and Ontologies
- Digital Mental Health Interventions
- Software Engineering Research
- Social Media and Politics
- Multimodal Machine Learning Applications
- Impact of Technology on Adolescents
- Spam and Phishing Detection
- Data Mining Algorithms and Applications
- Lexicography and Language Studies
- Data Quality and Management
- Mental Health Research Topics
- Anomaly Detection Techniques and Applications
- Machine Learning and Data Classification
- Text and Document Classification Technologies
- linguistics and terminology studies
- Mental Health via Writing
- Media and Communication Studies
- Multi-Agent Systems and Negotiation
Universidade Federal de São Carlos
2014-2025
Federal Institute of São Paulo
2022
Universidade de São Paulo
2006-2022
Instituto Federal do Piauí
2022
Weatherford College
2022
Brazilian Society of Computational and Applied Mathematics
2020
Consejo Superior de Investigaciones Científicas
2020
Instituto de Linguística Teórica e Computacional
2008
A formação de câmaras eco (echo chambers) consiste em um fenômeno no qual os usuários são frequentemente expostos a pontos vista que reforçam suas crenças, dificultando exposição perspectivas divergentes. Enquanto sabe-se do surgimento e da disseminação das se formam comunidades online, identificação automática compreensão deste surge como uma importante ferramenta para auxiliar investigação implicações na esfera política democracia. O objetivo artigo é investigação, implementação avaliação...
Machine learning (ML) is becoming critical to many businesses. Keeping an ML solution online and responding therefore a necessity, part of the MLOps (Machine Learning operationalization) movement. One aspect for this process monitoring not only prediction quality, but also system resources. This important correctly provide necessary infrastructure, either using fully-managed cloud platform or local solution. difficult task, as there are tools available. However, it requires some planning...
Depression has been one of the leading causes disability worldwide. In addition to conventional drugs and clinical treatments, other forms treatment are also available. For example, computational solutions have developed prevent, screen for, assist depression. More specifically, chatbots computer systems that used provide therapeutic support for individuals diagnosed with Although these commercially available, their design rationale evaluation still not fully validated, further research is...
In this paper we investigate the main linguistic phenomena that can make texts complex and how they could be simplified. We focus on a corpus analysis of simple account available web for Brazilian Portuguese (BP). This study illustrates need text simplification to facilitate accessibility information by poor readers people with cognitive disabilities. It also highlights features BP, which may differ from other languages. Moreover, propose strategies Simplification Annotation Editor. consists...
Multiword Expressions (MWEs) are one of the stumbling blocks for more precise Natural Language Processing (NLP) systems. Particularly, lack coverage MWEs in resources can impact negatively on performance tasks and applications, lead to loss information or communication errors. This is especially problematic technical domains, where a significant portion vocabulary composed MWEs. paper investigates use statistically-driven alignment-based approach identification corpora. We look at several...
This paper introduces NEMWEL, a system that performs Never-Ending Mul-tiWord Expressions Learning.Instead of using static corpus and classifier, NEMWEL applies supervised learning on automatically crawled news texts.Moreover, it uses its own results to periodically retrain the bootstrapping results.In addition detailed description system's architecture modules, we report manual evaluation.It shows is capable new expressions over time with improved precision.
In this paper we describe some experiments carried out to test the impact of automatic casing and punctuation changes when training testing statistical translation models. The described here concern from/to English Brazilian Portuguese texts but since superficial investigated are language independent, believe that conclusions can be applied many other pairs languages. These were designed aiming at setting a baseline scenario for future more complex models such as factored ones. From...
A internet e, em especial as mídias sociais, são um terreno fértil para a publicação de opiniões sobre os mais diversos assuntos, produtos e serviços. Tradicionalmente análise automática é realizada com base nas palavras que denotam alguma polaridade ou emoção. Contudo, o surgimento dos grandes modelos linguagem, como ChatGPT, maneira qual processamos textos realizar análises subjetivas mudou bastante. Neste contexto, este artigo tem foco investigar potencialidades do ChatGPT – comparada...
Technology plays a relevant role in mental health. Specifically, integrating pervasive technologies with artificial intelligence (AI) holds promising potential to collect users’ data, monitor individuals daily, and support treatment. However, the lack of trust collected data is common limitation prior work on health technology. This paper proposes involving user Human-in-the-loop approach as solution deal accuracy through In our study, end users judged evaluated at two different times:...