Marlo Souza

Universidade Federal da Bahia · Departamento de Ciência da Computação

We propose modeling different policies for behaviour diffusion in a network of agents considering conflict and dependency. In approaches based on the threshold-limited influence model, an agent adopts a behaviour if it has received enough influence from its social connections to surpass a given behaviour threshold. We also consider models where ado...

Nas universidades brasileiras, doutores e mestres lecionam em cursos de graduação, mestrado e doutorado em Computação. Contudo, alguns questionamentos sobre a formação didático-pedagógica desses educadores devem ser considerados. Neste artigo exploramos a formação didático-pedagógica de nove membros do corpo docente do Departamento de Ciência da Co...

A teoria de revisão de crença AGM provou ser uma abordagem frutífera para o estudo da mudança de crenças, mas com pouca flexibilidade para investigar fenômenos epistêmicos importantes. Em particular, enquanto as crenças são comumente aceitas como atitudes hiperintensionais, a literatura influenciada por AGM tem se concentrado principalmente em trat...

This work is an approach that brings together Learning Analytics and Ontologies for a data classification that promotes improvements and behavioral changes for students and teachers on e-Learning platforms. Combining training courses, dashboards, user's evaluations, and based on Design Science Research (DSR) methodology, artifacts were created. One...

This work compares POS and parsing systems for the Portuguese language. We analyse available features, tagsets, and compare the results of POS tagging, and syntactic structure identification by means of both intrinsic and extrinsic evaluation methods. For such, we use in this work well-known metric for parser evaluation such as bracket cross, leaf...

It is estimated that more than 80% of the information on the Web is stored in textual form. As such, it has become increasingly difficult for humans to sort and extract useful information from the daily influx of data. In order to automate this process, open information extraction (OIE) methods have been proposed, which can extract facts from large...

Computation Tree Logic is a temporal logic proposed as a tool for formal design and verification of concurrent systems in which execution flows may have many possible branches. A specification of a concurrent system may thus be constructed using a relational model for this logic, and the formal verification of the system’s properties may be carried...

Formal frameworks for Epistemology need to have enough logical structure to enable interesting conclusions regarding epistemic phenomena and to be expressive enough to model competing positions in the philosophical and logical literature. While beliefs are commonly accepted as hyperintensional attitudes, most work on standard epistemic logic has re...

Misinformation has plagued citizens’ lives, especially on social networks. During the COVID-19 pandemic, the proliferation of competing narratives and dissemination of false or inaccurate news about the pandemic has reached such a state that led the World Health Organization to classify it as an infodemic. However, few resources are available to co...

The university teacher education is a historical challenge constituted since the origin of the university itself because its primary nature is related to research. Computer Science training for Higher Education, in particular, represents a challenging theme in university reality and academic-scientific studies. In this sense, we present, in this ar...

Formal frameworks for Epistemology need to have enough logical structure to enable interesting conclusions regarding epistemic phenomena and to be expressive enough to model competing positions in the philosophical and logical literature. While beliefs are commonly accepted as hyperintensional attitudes, i.e., epistemic attitudes, which may differ...

O artigo aborda como a ética e a regulação afetam as tecnologias baseadas em IA e da linguagem humana, quando destaca que a linguagem está associada às estruturas sociais que a produzem. Uma das preocupações é a incorporação de vieses políticos em uma tecnologia baseada em IA. Por fim, chama atenção para a importância de garantir a transparência no...

Open Information Extraction (OpenIE) is the task of extracting structured information from text. Recent advances in applying Deep Learning to OpenIE tasks have improved the state of the art for the task, although few works have been produced for languages other than English. In this work, we propose PortNOIE, a neural framework for open information...

Automatic describing an image comprehends the representation from the scene elements to generate a concise natural language description. Few resources, particularly annotated datasets for the Portuguese language, discourage the development of new methods in languages other than English. Thus, we propose a new image captioning method for the Portugu...

The employment of video surveillance cameras by public safety agencies enables incident detection in monitored cities by using object detection for scene description, enhancing the protection to the general public. Object detection has its drawbacks, such as false positives. Our work aims to enhance object detection and image classification by empl...

Event Extraction (EE) is the task of identifying mentions of particular event types and their arguments in text, and it constitutes an important and challenging task within the area of Information Extraction (IE). However, in the context of the Portuguese language, very little work has been conducted on this topic. In this paper, we propose a neura...

Keeping track of student learning progress in the Distance Education it is a challenge for education specialists because it is always not possible to adopt the same evaluation mechanisms as traditional education due to transactional distance between educators and students. To help educators in the process of evaluating the acquisition of skills and...

Keeping track of student learning progress in Distance Education courses is a challenge for education specialists. It is not always possible to adopt the same evaluation mechanisms employed in traditional education due to transactional distance between educators and students. To help educators in the process of evaluating the acquisition of skills...

AGM's belief revision is one of the main paradigms in the study of belief change operations. Despite its popularity and importance to the area, it is well recognised that AGM's work relies on a strong idealisation of the agent's capabilities and the nature of beliefs themselves. Particularly, it is recognised in the literature that Belief and Knowl...

As different cloud computing services have emerged over the years, the diversity of technologies and the lack of standardization has given rise to an interoperability problem in cloud computing. Cloud computing services include those such as Software as a Service (SaaS), Platform as a Service (PaaS), Infrastructure as a Service (IaaS), and Data as...

AGM's belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been primarily used to specify the agent's belief state. While the connection of iterated AGM-like operations and their encoding in dynamic epistemic logics have been studied before, few works considere...

Este trabalho versa sobre as especificidades da política de formação inicial de professores no Curso de Licenciatura em Informática no Instituto Federal de Educação, Ciência e Tecnologia do Rio Grande do Norte. Trata das ações operacionalizadas no Programa Institucional de Bolsas de Iniciação à Docência (PIBID) em 03 (três) escolas na região da Zon...

AGM's belief revision is one of the main paradigms in the study of belief change operations. Recently, several logics for belief and information change have been proposed in the literature and used to encode belief change operations in rich and expressive semantic frameworks. While the connections of AGM-like operations and their encoding in dynami...

AGM's belief revision is one of the main paradigms in the study of belief change operations. Recently, several logics for belief and information change have been proposed in the literature and used to encode belief change operations in rich and expressive semantic frameworks. While the connections of AGM-like operations and their encoding in dynami...

AGM’s belief revision is one of the main paradigms in the study of belief change operations. Despite its popularity and importance to the area, it is well recognized that AGM’s work relies on a strong idealisation of the agent’s capabilities and on the nature of beliefs themselves. Particularly, it is well-recognized in the area of Epistemology tha...

Twitter is a social network and microblogging service where registered users read and post messages called tweets. Tweets have a maximum of 280 characters and cover every conceivable subject, from simple activity updates and news coverage to opinions about arbitrary topics. Therefore, Twitter emerges as a valuable data source to obtain information...

Open information extraction (Open IE) is the task of extracting open-domain assertions from natural language sentences. Considering the low availability of datasets and tools for this task in languages other than English, recently it has been proposed that multilingual resources can be used to improve Open IE methods for different languages. In thi...

AGM’s belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been primarily used to specify the agent’s belief state. While the connection of iterated AGM-like operations and their encoding in dynamic epistemic logics have been studied before, few works considere...

AGM's belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been primarily used to specify the agent's belief state. While the connection of iterated AGM-like operations and their encoding in dynamic epistemic logics have been studied before, few works considere...

While several BDI logics have been proposed in the area of Agent Programming, it is not clear how these logics are connected to the agent programs they are supposed to specify. More yet, the reasoning problems in these logics, being based on modal logic, are not tractable in general, limiting their usage to tackle real-world problems. In this work,...

In this work, we investigate the use of Dynamic Preference Logic to encode BDI mental attitudes. Further, exploring this codification and the representation of preferences over possible worlds by preferences over propositional formulas, here called priority graphs, we comment on how to interpret BDI agent programs in this logic. Also, using the con...

Os recursos da Web Semântica possibilitam a anotação semântica de Objetos de Aprendizagem (OA) auxiliando a sua busca e recuperação. Como o processo de anotação semântica manual é uma tarefa dispendiosa e geralmente dependente de domínio, o presente trabalho descreve um modelo para anotação automática de relações semânticas em OA utilizando ontolog...

This work presents an ontology to assist teachers in the process of evaluating the academic performance of distance education students. The purpose of this ontology is to infer about student's academic performance from the monitoring of student interactions in the Learning Management System. The ontology proposed represents two taxonomies consolida...

This work presents an ontology to assist teachers in the process of evaluating the academic performance of distance education students. The purpose of this ontology is to infer about the student's academic performance from the monitoring of student interactions in the Learning Management System. The ontology proposed represents two taxonomies conso...

The ability to follow learning progress and students’ performance can be beneficial to teachers and researchers in modern educational systems actions, especially in e-learning environments. In this paper, an effort is made to investigate and utilize the learning features sets from the learning objectives and students' interactions in Learning Manag...

AGM’s belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been largely used to specify the agent’s belief state - whether representing the agent’s ‘explicit beliefs’ or as a computational model for her belief state. While the connection of iterated AGM-like op...

A discussão sobre os processos de ensino e de aprendizagem tem sido tema de pesquisa em Ciência da Computação (CC) no Brasil e no exterior. A formação docente em CC para o ensino superior também deve ser temática de investigação e ação. Nesse sentido, este artigo apresenta uma ampliação no escopo de uma pesquisa inicial, apresentada anteriormente,...

The discussion about teaching and learning processes has been the subject of research in Computer Science (CS) in Brazil and abroad. Teacher training in CS for higher education should also be thematic of research and action. In this sense, this paper presents an expansion in the scope of an initial research, presented previously, with a quantitativ...

The number of documents published on the Web in languages other than English grows every year. As a consequence, the need to extract useful information from different languages increases, highlighting the importance of research into Open Information Extraction (OIE) techniques. Different OIE methods have dealt with features from a unique language;...

The number of documents published on the Web other languages than English grows every year. As a consequence, it increases the necessity of extracting useful information from different languages, pointing out the importance of researching Open Information Extraction (OIE) techniques. Different OIE methods have been dealing with features from a uniq...

AGM's belief revision is one of the main paradigms in the study of belief change operations. In this context, belief bases (prioritised bases) have been largely used to specify the agent's belief state - whether representing the agent's `explicit beliefs' or as a computational model for her belief state. While the connection of iterated AGM-like op...

A detecção (ou identificação) de paráfrases é a tarefa de determinar se duas ou mais sentenças de comprimento arbitrário possuem o mesmo significado. Os métodos para resolver esta tarefa com potenciais aplicações em sistemas de Processamento de Linguagem Natural. Este trabalho investiga a combinação de diferentes métodos de representação de sentenç...

Twitter is a social network and microblogging service in which registered users read and post messages called Tweets. Tweets have a maximum of 280 characters and cover every conceivable subject, from simple activity updates and news coverage to opinions about arbitrary topics. In this way, Twitter emerges as a valuable data source to get informatio...

AGM’s belief revision is one of the main paradigms in the study of belief change operations. Recently, several logics for belief and information change have been proposed in the literature, which were used to encode belief change operations in a rich and expressive framework. While the connection of AGM-like operations and their encoding in dynamic...

Ontologies are considered a necessary ingredient for communication among heterogeneous agents in the Web. With the multiplication of ontologies for the same domains, semantic interoperability has become a challenge. In this work, we study the use of ontology negotiation in a agent communication mechanism for agents with ontological reasoning. The r...

In this paper we present an overview of the language resources developed at the Natural Language Processing Lab at PUCRS, making them available to the research community.

Background: Open Information Extraction (Open IE) aims to obtain not predefined, domain-independent relations from text. This article introduces the Open IE research field, thoroughly discussing the main ideas and systems in the area as well as its main challenges and open issues. The paper describes an open extractor elaborated from the belief tha...

Open Information Extraction (Open IE) is an unsupervised strategy to draw out relations from text without predefining these relations, regardless the domain. This paper describes a novel Open IE approach that performs unsupervised extraction of triples by applying a few lexical-syntactic patterns to POS-tagged texts. In order to validate this strat...

This paper presents the algorithm Polarity Recognizer in Portuguese (PIRPO) to classify sentiment in online reviews. PIRPO was constructed to identify polarity in Portuguese user-generated accommodation reviews. Each review is analysed according to concepts from a do-main ontology. We decompose the review in sentences in order to assign a polarity...

This work presents an study on Sentiment Analysis on Twitter data for the Portuguese language. It evaluates the impact of different preprocessing techniques, Portuguese polarity lexicons and negation models showing low impact of preprocessing and negation modelling in classification of tweets.

Opinion Lexicons are linguistic resources annotated with semantic orientation of terms (positive and negative) and are important for opinion min-ing tasks. In the literature we see a variety of proposals for the construction of opinion lexicons using different linguistic resources and techniques. In this work, we propose and evaluate the integratio...