Brazil

Professional fact-checking tends to be costly and scalability challenges. For this reason, a series of methods to automate this process has been emerging. However, these methods have been created with monolithic architectures, not making use of pre-built parts, and are harder to be understood by others. This work aims to propose a framework, where the development of methods can be done in a modular manner, creating workflows based on key steps that can be linked together to generate the input classification. The framework makes use of a proposed data traceability ontology to map all generated data during execution under a unified vocabulary, which facilitates communication between these independent components.

BRACIS 2021

ReVera Framework: Um Framwork para rastreabilidade em fact-checking automático

fake enws

computer science

fact checking

natural language processing

**BRACIS** originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence – **SBIA** (22 editions), and the Brazilian Symposium on Neural Networks – **SBRN** (13 editions). **ENIAC** is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. **STIL** is the bi-annual Language Technology event.
All events are supported by the Brazilian Computer Society – Special Interest Groups: **CE-IA**, **CE-IC** and **CE-PLN**.

To access the 10th Brazilian Conference on Intelligent Systems (**BRACIS**), you need to register for the conference.  Please visit the Conference official site to register

[Register now](http://c4ai.inova.usp.br/bracis2021/)

Register now

Organized by C4AI, the 10th Brazilian Conference on Intelligent Systems (BRACIS) will take place from November 29th to December 3rd, 2021.

technical paper

O aprendizado multimodal visa explorar as características das diversas modalidades (texto, imagem, áudio) para gerar modelos computacionais. No comercio eletrônico, devido à grande variedade das características dos produtos e a ausência ou inconsistência de informações, a combinação de informações de modos diferentes vem a ser bastante adequada. Neste trabalho são apresentados alguns experimentos para a classificação multimodal (texto e imagem) de produtos (produtos adultos) que não podem ser vendidos no marketplace da empresa parceira. Nesses experimentos, redes neurais foram usadas para treinar classificadores uni e multimodal. O classificador multimodal atingiu 99% de F1 contra 98% do modelo textual e 94% do visual.

Classificacão multimodal de produtos que não podem ser vendidos no marketplace

Textual similarity deals with determining how similar two pieces of texts are, considering the lexical (surface forms) or semantic (meaning) close-ness. In this paper we applied word embeddings for measuring e-commerce product title similarity in Brazilian Portuguese. We generated some domain-specific word embeddings (using Word2Vec, FastText and GloVe) and compared them with general-domain models (word embeddings and BERT models). We concluded that the cosine similarity calculated using the domain-specific word embeddings was a good approach to distinguish between similar and non-similar products, but the multilingual BERT pre-trained model proved to be thebest one.

Measuring Brazilian Portuguese Product Titles Similarity using Embeddings

In this paper, we show how a Portuguese BERT model can be combined with structured data in order to deploy a chatbot based on a finite state machine to create a conversational AI system that helps a real-estate company to predict its client’s contact motivation. The model achieves human level results in a dataset that containts 235 unbalanced labels. Then, we also show its benefits considering the business impact comparing it against classical NLP methods.

Augmenting Customer Support with an NLP-based Receptionist

This work explores speech as a biomarker and investigates the detection of respiratory insufficiency (RI) by analyzing speech samples. 
Previous work constructed a dataset of respiratory insufficiency COVID-19 patient utterances and analyzed it by means of a convolutional neural network achieving an accuracy of $87.04\%$, validating the hypothesis that one can detect RI through speech. 
Here, we study how Transformer neural network architectures can improve the performance on RI detection. 
This approach enables construction of an acoustic model. By choosing the correct pretraining technique, we generate a self-supervised acoustic model, leading to improved performance ($96.53\%$) of Transformers for RI detection.

Audio MFCC-gram Transformers for respiratory insufficiency detection in COVID-19 disease

Depression is a psychological disorder that affects millions of people in the world, regardless of their age, social class, or nationality. Different techniques have been studied to analyze and recognize this disease in the literature, such as Natural Language Processing, Sentiment Analysis, and Machine Learning. However, in Brazilian Portuguese, only a few studies have been focused on creating a dataset to classify symptoms of depression. In this paper, we propose a novel text dataset composed of sentences that refer to the main symptoms of depression: behavioral, physiological, and psychological. Initial experiments exploring different machine learning algorithms in the dataset obtained high accurate performance values, which shows that the study is promising to encourage research in this area.

DP-Symptom-Identifier: uma estratégia para classificar sintomas de depressão utilizando um conjunto de dados textuais na língua portuguesa

A depressão é uma das questões de saúde mental mais preocupantes da atualidade. No Brasil, em 2019, 10,2% da população adulta relatou ter sido diagnosticada com depressão segundo dados da Pesquisa Nacional de Saúde. Identificar pessoas com perfil possivelmente depressivo permite um acompanhamento adequado por parte dos profissionais de saúde mental. Nesse sentido, as redes sociais online, como o Twitter, podem ser importantes aliadas. Este artigo apresenta experimentos realizados para a classificação automática de postagens (e não usuários) do Twitter contendo conteúdo que denota algum sintoma de depressão. A classificação com regressão logística apresentou os melhores resultados (F1 média de 57\%) entre os algoritmos investigados.

Identificando sintomas de depressão em postagens do Twitter em português do Brasil

Os danos causados por notícias falsas ou enganosas têm se potencializado graças à facilidade com que as informações são disseminadas em redes sociais. Durante a pandemia do Covid-19, iniciada em 2020, tais notícias foram capazes de gerar pânico na população, além de instruir erroneamente as pessoas sobre a prevenção da doença. O presente trabalho introduz um novo corpus a partir de postagens no Twitter na língua portuguesa com desinformações sobre a Covid-19. Além do novo corpus, o trabalho avalia diferentes abordagens de representações textuais e algoritmos de aprendizagem na tarefa de detecção de mensagens contendo desinformação. O melhor resultado obtido alcançou F1-score de 89% no modelo de classificação SVM com a representação textual TF-IDF.

Detecção de desinformação sobre Covid-19 no Twitter

Automatic text summarization aims at condensing the contents of a text into a simple and descriptive summary. Summarization techniques drastically benefited from the recent advances in Deep Learning. Nevertheless, these techniques are still unable to properly deal with long texts. In this work, we investigate whether the combination of summaries extracted from multiple sections of long scientific texts may enhance the quality of the summary for the whole document. We conduct experiments on real world corpus to assess the effectiveness of our proposal. The results show that our multi-section proposal are as good as summaries generated using the entire text as input and twice as good as single section.

A Long Texts Summarization Approach to Scientific Articles

In recent years, researchers in the area of Computational Creativity have studied the human creative process proposing different approaches to reproduce it with a formal procedure. We introduce a model for the generation of literary rhymes in Spanish, combining structures of language and neural network models Word2vec, into a structure for semantic assimilation. The results obtained with a manual evaluation of the texts generated by our algorithm are encouraging

A Preliminary Study for Literary Rhyme Generation based on Neuronal Representation, Semantics Resources and Shallow Parsing

The production of fake news is a problem nowadays. With social networks, fake news spread in easier and less costly ways, having the power to reach a large number of people in a short time. In this paper, we investigate graph-based approaches for fake news characterization and detection, taking into account widely used measures of graphs and complex networks. Our results show that some network measures are useful for structurally characterizing fake and true news and that machine learning-based solutions over this kind of feature produce promising results.

ReVera Framework: Um Framwork para rastreabilidade em fact-checking automático

Downloads

Next from BRACIS 2021

Classificacão multimodal de produtos que não podem ser vendidos no marketplace

Similar lecture

An Empirical Study of Text Features for Identifying Subjective Sentences in Portuguese

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES