Brazil

Na área de Sistemas de Recomendação existe uma predominância histórica para algoritmos colaborativos em relação à baseados em conteúdo. No entanto, o último pode apresentar melhores resultados com usuários e ser mais transparente que o primeiro. Dessa maneira, será apresentado o algoritmo de recomendação baseado em conteúdo WordRecommender, que calcula proximidade de itens a partir da similaridade semântica entre os aspectos mais importantes de cada um, extraídos a partir de revisões de usuários. Para produzir explicações textuais, o algoritmo pode utilizar a mesma métrica semântica considerando um filme de perfil e um outro recomendado. Como resultado, o método proposto apresentou um desempenho melhor que os baseline em contextos de pouca quantidade de dados e vizinhos, evidenciando que dados semânticos são uma fonte importante para representação de informação e explicações em sistemas de recomendação.

WebMedia 2020

WordRecommender: An Explainable Content-Based Algorithm based on Sentiment Analysis and Semantic Similarity

análise de sentimento

explicações

sistemas de recomendação baseados em conteúdo

sistemas de recomendação

processamento de linguagem natural

**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

BRACIS 2021

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

technical paper

Promoted by the Brazilian Computer Society (SBC), the Brazilian Symposium on Multimedia and Web (WebMedia) is the main event of the theme in Brazil and an excellent opportunity for scientific and technical exchange among students, researchers and professionals in the areas of Multimedia, Hypermedia and Web. This year we will be celebrating to 26th edition of WebMedia, which will be held online from november 30th to December 4th .

Webmedia 2020’s programming includes:

– Technical sessions for the presentation of scientific papers
– National and international keynotes
– Panel with companies
– Workshops
– Short Courses
– Open community meetings

The topics of interest for submitting papers are:

– Web and Social Networks
– Multimedia
– Digital TV, Ubiquitous and Mobile Computing

Besides the main track, WebMedia 2020 will have in parallel the Tools and Applications Workshop, works Tools and Applications Workshop, the Workshop on Undergraduate Research Work and the Workshop The Future of Interactive.

The WebMedia 2020 organization is under the responsibility of the Programa de Pós-graduação Doutorado em Ciência da Computação – Associação UFMA/UFPI (DCCMAPI), do Programa de Pós-graduação em Ciência da Computação/ CCET (PPGCC), do Laboratory of Advanced Web Systems/UFMA (LAWS) e do Laboratório de Sistemas Multimídia/UFMA (TELEMÍDIA).).

#PartiuWebMedia2020 #WebMedia2020

Promoted by the Brazilian Computer Society (SBC), the Brazilian Symposium on Multimedia and Web (WebMedia) is the main event of the theme in Brazil and an excellent opportunity for scientific and technical exchange among students, researchers and professionals in the areas of Multimedia, Hypermedia and Web.

Distinct Data as a Service (DaaS) and Database as a Service (DBaaS) providers can store and manage heterogeneous data in the cloud. Data are accessed from the Software as a Service (SaaS) through an automated solution named MIDAS (Middleware for DaaS/DBaaS and SaaS), which is an intermediate communication layer between SaaS and DaaS/DBaaS. During the providers' evolution, a SaaS query may be affected by DaaS attributes' change. The challenge is to ensure data cloud services consistency for consumers can access the correct attribute when querying a DaaS. Thus, we propose a method to match semantic similarity among DaaS attributes. The method combines two steps to track semantic similarities of DaaS attributes. The first step is done by Cosine and Jaccard measures (edge-counting approach) to identify the number of edges linking two attributes to find the syntactic or lexical similarity, and the second step performed by Information Content (IC)-based measures with WordNet to assess the semantic similarity if edge-counting measures are unable to provide parity between DaaS attributes. Our method is implemented in MIDAS middleware as a proof of concept, and we perform some experiments to evaluate three criteria: overhead, performance, and correctness of our approach. Results showed that we are in a potential direction to provide semantic interoperability between SaaS and DaaS.

Semantic similarity attributes for Data Cloud: A case study in MIDAS

The candidate's thesis is within the emerging topic of mulsemedia systems, which encompass audiovisual content associated with multisensory effects, users' quality of experience, and human-computer interaction. It presents a conceptual architecture and a framework that take into account the challenges and requirements for mulsemedia delivery systems identified from the gaps and shortcomings in related work. Furthermore, the work's outcome brings multiple and valuable contributions relying on a complex and solid experimental setup, which have been shared and published in relevant journals and conferences.

A Conceptual Architecture and a Framework for Dealing with Variability in Mulsemedia Systems

In this work, we present the platform Boca a Boca Virtual, a kind of virtual catalog that aims to help self-employed professionals and small businesses to start their presence in the digital environment, promoting their services and products in a simple and fast way. The idea emerged during the beginning of the COVID-19 pandemic, especially with social isolation, whose concern, from an economic and social point of view, was to allow autonomous service providers and establishments, in general, to continue offering their products and/or services. Through the platform, a consumer can search for a specific product and service within his own neighborhood and city, strengthening the local economy. In addition, Boca a Boca Virtual is integrated with Google Maps, in such a way that registered developments are also indexed by the Google search engine, improving their visibility and potentially increasing more customers. The platform is fully responsive, combining several recent web development technologies. Today it has more than 140 registered enterprises, from more than 30 Brazilian cities.

Boca a Boca Virtual: Presença Digital para Pequenos Empreendedores

This work aims to present the platform on government accountability. named “Cuidando do Meu Bairro” ("Caring for My Neighborhood"), which is a social platform for monitoring and controlling the town´s public spending. The work shows its concept evolution based on stakeholders feedback during the last 8 years that the platform has been contributing to governmental accountability and social participation, The functionalities and software architecture are presented. Also, the main outcomes and social impact that this project provided on civic education, fight against corruption, public transparency and social participation are briefly presented.

Cuidando do Meu Bairro 2.0: Acesso à informação e monitoramento dos gastos da cidade em tempo real

Entering the world of Interactive Digital Television (iDTV) applications can lead to an exhaustive process that involves reading extensive standards and may need a robust middleware solution to run Ginga-NCL applications, which is a subset of Ginga and the standard for interactivity of digital television adopted in Latin America countries. Even though there are some open and commercial solutions for development of Ginga applications available on the market, most of these solutions present downsides such as deep dependency of Ginga engine implementation, need of complex environment setup and they are not very intuitive NCL/NCLua coding platforms. To solve these issues, we created an IDE developed in web technology that makes possible for students and professionals to learn how to develop Ginga-NCL applications. With this tool, developers can write, validate and experiment their applications entirely on the web environment, with no software installation required.

NuGinga Playcode: A web NCL/NCLua authoring tool for Ginga-NCL digital TV applications

The COVID-19 pandemic had substantial impacts on society, both socially and economically, with devastating impacts on our country. Aiming at assisting on coping with such pandemic and providing relevant information for society on matters such as the portion of the population under quarantine, details on philanthropic institutions and the location of health Units, we developed FiscalCovid. Using geoprocessing and crowdsourcing techniques, this system enables the social control as a support tool for the battle against COVID-19.

FiscalCovid: exercendo o controle social na temática da COVID-19

Currently, so-called Recommendation Systems (SRs) have been used to assist users in discovering relevant Points of Interest (POIs) on Location-Based Social Networks (LBSN), such as FourSquare and Yelp. Given the main challenges of data-sparse and geographic influence in this scenario, most of the work on POI recommendations has focused only on improving the effectiveness (i.e. accuracy) of the systems. However, there is a growing consensus that just effectiveness is not sufficient to assess the practical utility of these systems. In real scenarios, categorical and geographic diversities were identified as the main complementary dimensions for assessing user satisfaction and the usefulness of recommendations. The works in the literature are concentrated on only one of these concepts. In this work, we propose a new post-processing strategy, which combines these concepts in order to improve the user’s interest in POIs. Our experimental results in the Yelp data sets show that our strategy can improve user satisfaction, considering different SRs and multiple diversification metrics. Our method is capable of improving diversity by up to 120% without significant losses in terms of effectiveness.

Estratégias para Aprimorar a Diversidade Categórica e Geográfica de Sistemas de Recomendação de POIs

Learning verification is the target of numerous studies that aim to
transform it from its solely classificatory character, in a process of
diagnosing the student's evolution in the learning goals of a
subject. This research proposes a software for monitoring and
authoring evaluative activities, modelled in order to support
teachers and students in the learning verification process. For this,
using the DSR methodology, a bibliographic study was carried out
in the context of school evaluation to support the designing of the
tool. The presented solution was validated through tests and
questionnaires on user experience. The results demonstrated the
potential of the tool to support the school evaluation process.

Avaliar: Sistema para Autoria e acompanhamento de recursos avaliativos

Lack of physical distancing, isolation, and social interactions are
some of the key factors that have contributed to the spread of
COVID-19 and transformed it into this global pandemic. Combining
and correlating human mobility with the COVID-19 cases being
reported may help to determine possible hotspots and provide
guidance on how to possibly make lifestyle changes and choices
so as to avert/limit future waves of this pandemic or a similar one.
This project aims to cope with the research problems involved in
the development of a graphical and interactive tool that performs
intelligent data analysis of visually selected geo-temporal subsets
of collected information. As a result of the project, it was launched
the COVID-19 Borescope, which is shown in Figure 1.

COVID-19 Borescope

In different countries, govern transparency is widely accepted as an effective democratic process. In Brazil, the information-access law contributes to public administration transparency since various public data are available on the Web. However, such data are in different formats and not standardized which makes it difficult to obtain information, mainly in an automated way. Indeed, this work presents an enrichment in an existing open Brazilian judiciary database, a characterization of the available data, and an analysis of the data about judiciary professionals and their earns. The results reveal a lack of linear correlations between the high salaries and their personal benefits. Also, there is a discrepancy between Judiciary salaries and advantages through Brazilian regions, which may be explained by the higher living costs in some regions.

WordRecommender: An Explainable Content-Based Algorithm based on Sentiment Analysis and Semantic Similarity

Downloads

Next from WebMedia 2020

Semantic similarity attributes for Data Cloud: A case study in MIDAS

Similar lecture

PetroGold - Corpus padrão ouro para o domínio do petróleo

WordRecommender: An Explainable Content-Based Algorithm based on Sentiment Analysis and Semantic Similarity

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from WebMedia 2020

Semantic similarity attributes for Data Cloud: A case study in MIDAS

Similar lecture

PetroGold - Corpus padrão ouro para o domínio do petróleo

Downloads