Brazil

Extracted from Wikipedia content, DBpedia is considered one of the most important knowledge bases of the Semantic Web, which has editions in several languages, among which those in English (DBpedia EN) and Portuguese (DBpedia PT). All DBpedia editions are subject to quality issues, more especially DBpedia PT suffers from inconsistencies and lack of data in several domains. In this talk, we describe a semi-automatic and incremental process for publishing data on DBpedia, coming from reliable external sources, while seeking to improve aspects of its quality. In an open science context, the proposal aims at consolidating DBpedia as a reference hub for research data, so that research from any area supported by the Semantic Web data can use its data reliably.

WebMedia 2020

An Approach for Improving DBpedia as a Research Data Hub

dbpedia

data quality

open science

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

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.

Whatsapp is the most popular messaging app in the world. It is not only used as a one-to-one messaging app but also as a platform for group discussion. Recently, Whatsapp has gained the spotlight for its role in disseminating (often low-quality) information. Our study focuses on YouTube videos shared by political-oriented public groups on Whatsapp for a month during the COVID-19 pandemic. Through a careful analysis of the topical distribution and the lexicon present in the videos shared, we shed light on the COVID-19 debate happening in these groups. Moreover, we compare COVID-19 related videos with other political videos being shared in the groups. We observe that videos that discuss political themes have more emotional attributes as well as topics related to typical right-wing concerns such as family, work, and religion than videos discussing both pandemic and politics.

Analyzing YouTube Videos Shared on Whatsapp in the Early COVID-19 Crisis

Currently, most declarative languages used to define multimedia
documents do not support the specification of an interactive ap-
plication with multiple users and multimodal interaction. To han-
dle multimodal and multi-user interaction in these languages, the
author of multimedia applications must write custom code in an
imperative language to be included in the declarative document.
To fill in this gap, this work proposes an extension of NCM (Nested
Context Language), NCL (Nested Context Language) and Ginga-
NCL to provide high-level abstraction multimodal and multi-user
interaction specifications. As a proof of concept, we developed a
multimedia application that uses multi-user voice interaction.

Extending Ginga-NCL to Specify Multimodal Interactions With
Multiple Users


Nowadays, news websites are the main sources of information for most people. But these outlets may have a bias in their publications, favoring some ideology. This can influence people’s opinion regarding several topics. Methods to automatically detect bias are usually based on aspects such as text and embedded hyperlinks. In this work, we present a strategy to detect media bias by analyzing networks that model citations between news websites, evaluating if the bias is related to structural characteristics of these networks. We show that ideological bias can be captured by citation patterns and present a method that uses these patterns to automatically identify political bias in news websites, reaching accuracy and F1 scores above 72% and 0.70, respectively.

An Evaluation of Structural Characteristics of Networks to Identify Media Bias in News Portals

Techniques in recommendation systems generally focuses on recommending the most important items for a user. The purpose of this work is to generate recommendations focusing on long tail items, leading users to less popular and at the same time highly relevant products. Two techniques from the literature were applied in this study. The first technique is through graphs to calculate node similarity between users and items. The second technique applies clustering in the set of items in a dataset. This combination was adopted in order to give more visibility to long tail items. To evaluate the proposed approach an experiment was carried out to calculate the accuracy, diversity, and popularity of the generated recommendation. We compare the proposed approach with other 3 baselines where our approach achieved better results.

Exploiting Graph Similarities with Clustering to Improve Long Tail Items Recommendations

Early fusion techniques have been proposed in video analysis tasks as a way to improve efficacy by generating compact data models capable of keeping semantic clues present on multimodal data. First attempts to fuse multimodal data employed fusion operators at low-level feature space, losing data representativeness. This drove later research efforts to evolve simple operators to complex operations, which became, in general, inseparable of the multimodal semantic clues processing. In this paper, we investigate the application of early multimodal fusion operators at the mid-level feature space. Five different operators (Concatenation, Sum, Gram, Average and Maximum) were employed to fuse mid-level multimodal video features. Fused data derived from each operator were then used as input for two different video analysis tasks: Temporal Video Scene Segmentation and Video Classification. For each task, we performed a comparative analysis among the operators and related work techniques designed for these tasks using complex fusion operations. The efficacy results reached by the operators were very close to those reached by the techniques, pointing out strong evidence that working on a more homogeneous feature space can reduce known low-level fusion drawbacks. In addition, operators make data fusion separable, allowing researchers to keep the focus on developing semantic clues representations.

Evaluating Early Fusion Operator at Mid-Level Feature Space

Information and Communication Technologies present as an interesting alternative for the mitigation of barriers that arise in the context of communication of information, mainly as technologies aimed at the machine translation of content in oral language into sign language. After years, despite the improvement of these technologies, the use of them still divides the opinions of the Deaf Community, due to the low emotional expressiveness of 3D avatars. This study aims to explore a strategy of analyzing emotions in texts to use in machine translators from Brazilian Portuguese to LIBRAS, in order to make the experience of using these technologies more satisfactory. The analysis of emotions in texts presents a relevant challenge in diversity due to the nuances and different forms of expression that the human language uses. In this context, the use of deep neural networks has gained enough space as a way to deal with these challenges, mainly with the use of algorithms that deal with emotion analysis as a textual classification task, such as the MultiFiT approach. To circumvent the scarcity of data in Brazilian Portuguese aimed at this task, some strategies for data augmentation were evaluated and applied to improve the database used in training. The results of the emotion analysis experiments with Transfer Learning pointed to accuracy above 94% in the best case.

Using Data Augmentation and Neural Networks to Improve the Emotion Analysis of Bazilian Portuguese Texts

Identifying suspects of crimes on social networks is one of the most relevant tasks in the analysis of this type of network. Most of the computational methods focused on this task involve supervised machine learning, and, therefore, require previously labeled datasets that inform, among the registered people, which ones are suspects. However, in practice, this type of information is not available, for several reasons, among which, it is rare or even protected by secrecy guaranteed by law. This limitation makes it very difficult to effectively use these methods in real situations. Hence, the present work raises the hypothesis that the use of a controlled vocabulary on the field of application can make it possible the identification of suspects in social networks, without the need for previously labeled datasets. In order to search for experimental evidence that points to the validity of the hypothesis raised, this article proposes a method that uses a controlled vocabulary with categorized terms, according to a certain domain (e.g., pedophilia, cyberbullying, terrorism, etc.), to analyze messages exchanged on social networks, in order to identify criminal suspects. The results obtained in a preliminary experiment showed signs of adequacy of the proposed method.

Identifying Criminal Suspects on Social Networks: A Vocabulary-Based Method

The recent growth of social networks led to an increase in the dissemination of hate speech online and, as a consequence, studies about hate speech detection have emerged. Part of them are based on supervised learning techniques, which require large labeled databases, however this is still a scarce resource. Most of the existing databases on hate speech consist of texts in English. Although there are some databases in Portuguese, they are rather small with few examples, a factor which can limit both the performance of simple deep neural networks and the usage of more complex architectures. In order to work around this setback, this paper analyses the usage of Data Augmentation in texts to improve the training performance of recursive neural networks (LSTM) and convolutional neural networks (CNN) applied to the hate speech detection task. Data Augmentation is a regularization process used on deep neural networks to avoid overfitting. These techniques are common in the field of computer vision, however, due to the complexity of natural languages, this process is not as frequently used in tasks involving texts. In this paper, we experimented on a public hate speech database in Portuguese using Data Augmentation techniques such as text generation from the original database to enhance the results. The experiments show an improvement in the results, demonstrating that the techniques are promising.

Data Augmentation for improving Hate Speech Detection on Social Networks

The constant expansion of e-commerce, recently boosted due to the coronavirus pandemic, has led to a huge increase in online shopping. More and more, customers demand online reviews of products and comments on the Web to make decisions about buying a product over another. In this context, sentiment analysis techniques constitute the traditional way to summarize user’s opinions that criticizes or highlights the positive aspects of a product. Sentiment analysis of reviews usually relies on extracting positive and negative aspects of products, neglecting comparative opinions. Such opinions do not directly express a positive or negative view but contrast aspects of products from different competitors. In this paper, we present the first effort towards detecting comparative sentences in Portuguese. Identifying comparative sentences is a key task for companies to know how users are comparing a product with their competitors and is essential for developing sentiment summarization applications for the end user. In addition, we present a supervised approach to automatically detect Portuguese comparative sentences, classifying them into five distinct groups: (1) Non-Comparative, (2) Non-Equal Gradable, (3) Equative, (4) Superlative e (5) Non-Gradable. To that end, this paper provides three main contributions: (1) a Portuguese lexicon list with words used to make comparisons; (2) two new Portuguese datasets with comparative sentences; and (3) a hierarchical approach for detecting multiple comparisons and classify the sentences in different groups by using state-of-art classification algorithms, reaching an accuracy of 87%.

Mining Portuguese Comparative Sentences in Online Reviews

The Internet of Things (IoT) is an increasingly evident reality in everyday life. IoT makes possible to interconnect physical objects through a heterogeneous computer network, creating new ways to manage infrastructures. In the IoT systems, smartphones have a fundamental role due to their computational capacity and resources. Nowadays, the major mobile devices have several types of sensors that can be used to monitor and collect data from the physical world, such as GPS, accelerometer, barometer, among others. Thus, IoT developers have used different cross-platform frameworks to improve their productivity and to make the software maintainability easily and fast. In this context, the goal of this work is to understand the performance impacts of some cross-platform frameworks for IoT application development. To do this, we built three versions of the same Android application of an IoT system using (1) Ionic, (2) React Native, and (3) Java, which uses some smartphone's sensors commonly used in IoT applications, such as GPS, WiFi, and BLE. For each resource and performance evaluation metric for each version of our application, we created a specific test-case to measure and to compare the analyzed cross-platform framework. Our results showed slight differences between the three versions of our IoT application in some analyzed metrics.

Downloads

Next from WebMedia 2020

Analyzing YouTube Videos Shared on Whatsapp in the Early COVID-19 Crisis

Similar lecture

An Industry Evaluation of Embedding-based Entity Alignment

.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

Analyzing YouTube Videos Shared on Whatsapp in the Early COVID-19 Crisis

Similar lecture

An Industry Evaluation of Embedding-based Entity Alignment

Downloads