Sandro José Rigo

Automatic Information Extraction from Texts with Inference and Linguistic Knowledge Acquisition Rules

In this paper we present a novel methodology for automatic information extraction from natural language texts, based on the integration of linguistic rules, multiple ontologies and inference resources, integrated with an abstraction layer for linguistic annotation and data representation. The methodology allows ontology population with instances of events. The main contribution presented is related to the exploration of the flexibility of linguistic rules and domain knowledge representation, through their manipulation and integration by a reasoning system. The results from the case study indicate that the proposed approach is effective for the legal domain.

DeCom: A model for context-aware competence management

Abstract This article proposes a model of a context-aware system, called DeCom, to support competence management. The model considers the profiles of employees in organizations and the contexts in which they are involved, looking for opportunities to help them to develop their competences. DeCom proposes a Context Model organized into five categories, which enable the mapping of employees’ mobility and development, using context-based information (people, events and other resources). Moreover, the model proposes a Competence Model specifically oriented towards contexts. A case study involving an Enterprise Resource Planning (ERP) vendor enabled data collection based on realistic scenarios. The model was implemented based on multiplatform programming for mobile devices. This prototype and the case study were used in an evaluation involving the IT manager from the ERP vendor. The specialized evaluator executed eight scenarios to test the functionalities of DeCom. The article discussed the result of this evaluation and describes three scenarios in detail to better demonstrate how DeCom explores the employees context in a business environment. Moreover, the article summarizes an acceptance evaluation conducted with twenty-one volunteers to test the DeComs usability. The results were encouraging and show the potential for implementing DeCom as a tool to foster the competence management in organizations and to support corporate education activities.

Aplicações de Mineração de Dados Educacionais e Learning Analytics com foco na evasão escolar: oportunidades e desafios

Este artigo, tendo como foco o quarto desafio da SBC, o qual trata do “Acesso participativo e universal do cidadao brasileiro ao conhecimento”, apresenta uma analise de melhorias possiveis na aplicacao de Mineracao de Dados Educacionais, para que seus resultados possam apoiar efetivamente processos de deteccao de comportamentos ligados a evasao escolar. E demonstrada a importância de um amplo mapeamento de fatores associados, bem como a necessidade de implantacao de solucoes interativas, que possibilitem o acesso dinâmico aos resultados, permitindo o diagnostico precoce e a realizacao de acoes pedagogicas. Ao final deste artigo algumas questoes relevantes ao topico mineracao de dados educacionais sao abordadas visando fomentar a discussao de oportunidades nesta area.Este artigo, tendo como foco o quarto desafio da SBC, o qual trata do “Acesso participativo e universal do cidadao brasileiro ao conhecimento”, apresenta uma analise de melhorias possiveis na aplicacao de Mineracao de Dados Educacionais, para que seus resultados possam apoiar efetivamente processos de deteccao de comportamentos ligados a evasao escolar. E demonstrada a importância de um amplo mapeamento de fatores associados, bem como a necessidade de implantacao de solucoes interativas, que possibilitem o acesso dinâmico aos resultados, permitindo o diagnostico precoce e a realizacao de acoes pedagogicas. Ao final deste artigo algumas questoes relevantes ao topico mineracao de dados educacionais sao abordadas visando fomentar a discussao de oportunidades nesta area.

Developing a ubiquitous tourist guide

In the tourism area, the use of mobile devices brings significant benefits, considering the associated mobility, the instant access and the quality of the tourist information provided. One of the applications in this field is the electronic tourist guide, which provide information to tourists to better enjoy their trip. In this perspective, this work proposes a model that uses mobile and ubiquitous tourism concepts to improve tourist experience. We had developed a prototype for iOS focused on the Caminhos de Pedra tourist itinerary, in Bento Gonçalves / Rio Grande do Sul. Using this prototype, we carried on two evaluations, regarding the ontology proposed and usability. As a result, we could verify that the proposed model helps people to better experience their trips.

A model for data integration in open and linked databases with the use of ontologies

In Brazil, the access to Information Act (Act/12527 2011), fosters the availability and the access to data of interest to the citizen. However there is a lack of resources to conduct the integration of information originating on open databases. This work presents the development of resources to infer and relate information in the context of Web applications geared to the integration of open databases and connected. It was implemented a prototype that used the government procurement and budget data, seamlessly, from the resources of the model. As a result, it was found that the model implemented provided the desired integration and helped users get a better experience when viewing linked data of government procurement with the federal budget.

A proposal for managing multiple trails in educational environments

Mobile computing and localization systems recent diffusion enables the use of contexts and trails in several applications, with the incorporation of resources for content adaptation and distribution. A trail represents a set of user contexts, historically organized. This article presents a proposal for managing multiple trails in mobile computing environments. Its differential is the representation of the data of each entity in several trails. This approach allows the multiple aspects of interest for the entity to be modeled and stored. In addition, facilitates its use in different applications, which may need only part of the elements in this set of trails. In this way, this proposal extends the possibility of context composition for entities, providing greater flexibility to their use. This is demonstrated in two case studies of the application of this model.

Diagnosis of learner dropout based on learning styles for online distance learning

Abstract The amount of data generated by computer systems in Online Distance Learning (ODL) contains rich information. One example of this information we define as the Learner Learning Trail (LLT), which is the sequence of interactions between the students and the virtual environment. Another example is the Learner Learning Style (LLS), which is associated with the student behavior and choices during the learning process. This information can be used to identify learner behavior and learning style. We perceived, after the study of related literature, that the research field of learner diagnosis for ODL does not apply the conjoint use of LLT and LLS. In this article, we propose a model capable of integrating data generated from the behavior of students in ODL with cognitive aspects of them, such as their Learning Styles, by crossing LLT with LLS. We also propose the CPAD method (Collect, Preprocessing, Analysis, Diagnosis), which is implemented by collecting the raw data regarding learning activities, preprocessing the data into structured time sequences, analyzing the sequences regarding the learning styles and using this analysis to diagnose the learner behavior. We selected the dropout to investigate, once the dropout rate in ODL is a real problem in universities around the world. In addition, the dropout is a student decision which can be associated with previous students behaviors. We performed a study with 202 learners to evaluate if learning styles are capable of explaining aspects of the student behavior. The results suggest that Sequential/Global learning style dimension is more capable of explaining the dropout than the other dimensions. Also, we performed four classification experiments to verify how the dimensions of Felder-Silverman Learning Style Model influence the learner diagnosis. We perceived that the Sequential/Global dimension could provide a higher accuracy average with lower variation independently of the diagnosis technique.

Enhancing Brazilian Portuguese Textual Entailment Recognition with a Hybrid Approach

Previous work on textual entailment has not fully exploited aspects of deep linguistic relations, which have been shown as containing important information for entailment identification. In this study, we present a new method to compute semantic textual similarity between two sentences. Our proposal relies on the integration of a set of deep linguistic relations, lexical aspects and distributed representational resources. We used our method with a large set of annotated data available from the ASSIN Workshop in the PROPOR 2016 event. The achieved results score among the best-known results in the literature. A perceived advantage of our approach is the ability to generate good results even with a small corpus on training tasks.

Development of a Recommender System to the Virtual Patient Simulator Health Simulator

This paper presents a recommender system on clinical cases and materials that may help the student in the learning process. The experiment involves the development of collaborative and content based filters and also three hybrid methods. The system was qualitatively evaluated, using accuracy metrics in prediction and classification tasks. The obtained results show promising values on the collaborative filters.

Ontology-based information extraction for juridical events with case studies in Brazilian legal realm

Abstract The number of available legal documents has presented an enormous growth in recent years, and the digital processing of such materials is prompting the necessity of systems that support the automatic relevant information extraction. This work presents a system for ontology-based information extraction from natural language texts, able to identify a set of legal events. The system is based on an innovative methodology based on domain ontology of legal events and a set of linguistic rules, integrated through inference mechanism, resulting in a flexible approach and scalable approach. A case study with the use of documents from the Superior Court in Brazil is related, with satisfactory results in precision and recall.