Brazil

Wikipedia, with more than 50 billion pages, is one of the most popular free online encyclopedias in the world. It is based on user-generated content, in other words, anyone with internet access can write and make changes to its articles, hence the information quality of the encyclopedias is often criticized. Therefore, assigning the correct class of quality to Wikipedia articles is crucial for the experience of both authors and readers when using this large repository of information. In this paper, we present an approach relying on deep neural networks for quality classification of Wikipedia articles. The experiments consisted of testing three different models to achieve the best possible result: the first one using a model without multiview, the second using multiview with three views and the third one using multiview with six views. Finally, we compared our results with a model that used Support Vector Regression as the learning algorithm, achieving similar values with our multiview models.

WebMedia 2020

Automatic Content Quality Estimation Using Deep Neural Networks in Collaborative Encyclopedias on the Web

machine learning

wikipedia

deep neural networks

### Welcome!
The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. Our Virtual Poster Sessions will take place online Thursday, August 22, 2024.

You are required to register for this event. **Please register [here](https://2024.aclweb.org/registration). **

If you have already registered, please check your inbox for an email from Underline granting you access to ACL 2024 content.

Please register!

ACL 2024

The 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024) will take place in Bangkok, Thailand from August 11th to 16th, 2024. More information will be announced soon.

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.

In Brazil, 2010, more than 6.5 million people claimed to have some visual impairments. Software and Web accessibility are becoming first-class requirements to promote a better relationship between those people with visual impairments and the internet as well as with new digital technologies. However, designers and software developers need more empathy and knowledge about these groups’ issues to implement accessibility features into their digital products correctly (e.g., apps, games, Web sites). This paper has the goal of developing an eye disease simulator (SDO - Simulador de Doenças Oculares) for mobile devices, which could help better teach and illustrate the effects of these diseases. First, we investigated how to simulate the symptoms of each disease better and have developed the SDO mobile application. SDO is capable of both simulating different types of Colorblindness as well as other more dangerous eye illnesses (i.e. Glaucoma, cataracts). The current version also supports the use of Head-Mounted Displays to increase user immersion.

SDO: Simulador de Doenças Oculares

Regarding ontology editors, it is observed that there are several gaps left by the main tools available on the web for editing and viewing ontologies. The proposal for this work is to provide more efficient and effective editing interfaces, providing a practical tool that improves the visualizing OWL graphs.

KGWE - A customizable editor for OWL ontologies

Nowadays, we face a considerable improvement in education technologies, yet children's spelling assessment is still a paper-and-pencil based method. Since it is a regular activity in literacy classrooms and has to be conducted individually with each child, it is a laborious task for a teacher. It is challenging to offer an optimal number of tests because of the number of students in a single class. Moreover, the pandemic period highlighted the need for digital resources to support this activity remotely. In this context, we are developing a method for conducting automated word dictation sessions and support teachers in identifying children spelling development stages. Using DSRM, we believe that we can provide not only offering a more playful writing experience for children through technology, also to reduce teacher overload in the classroom. As preliminary results, the proposal was validated by usability inspection, and the results are promising.

Aplicativo para sondagem de hipótese de escrita infantil remota

People with visual impairments suffer from the incapacity to un-derstand contextual information in videos, such as the place wherecharacters are, or any other non-spoken actions in general. Somecontent creators address this issue by providing a secondary audioto describe such information, calledAudio Descriptions(ADs). How-ever, some works in the literature have highlighted that people withvisual impairment are usually not able to completely understandscene changes based only on characters’ voices or traditional ADs.Moreover, traditional ADs do not completely describe some of theimportant visual information, such as the background scenery (e.g.colors, furniture) and characters’ details (e.g. blond woman using ared dress). In this work, we propose incrementing the traditionalAD techniques with the usage of interactive video features presentin TV systems. More precisely, the proposed interactivity enablesusers to access specialized AD for different visual information (e.g.,scene, scenario, character). To support the development of such in-teractive content, we present an application template, which helpsto create the final interactive-enhanced video application. As aproof of concept for our approach, we created an interactive ADfor an independent video mainly composed of visual information,with only a few talks.

ListeningTV: Accessible Video Using Interactive Audio Descriptions

Technological resources have become indispensable in professional sports activities due to the critical level of competitiveness of athletes required in tournaments. One of the main aspects that characterize a volleyball athlete's success is his performance in the jumps performed during a match. This physical action is performed several times by the athlete to attack or prevent the success of an opposing team's attack. Wearable computing has become common in sports training, just as there are approaches that use sensors attached to the athletes' body to study and quantify the jump's movement. However, these marketable portable devices tend to be used as activity trackers that provide simple recommendations, such as the number of steps, heart rate, distance traveled, and amount of calories lost. Besides, real-time monitoring and evaluation solutions to provide personalized feedback and decisions are expensive and not viable for athletes without sponsorship.
For this reason, this work presents VolleyJump 2.0, a computational approach to classify volleyball athletes jumps using techniques of extraction and selection of features from digital signals provided by inertial sensors. The performance results of the data set are also presented, in a promising way, in some machine learning models developed to predict volleyball jumps. Recent studies dealing with this topic show that classification models have good results for distinguishing jumps using a device that contains an accelerometer and gyroscope sensor. In this study, we proposed using prototypes of electronic devices of inertial sensors attached to the wrist and waist of the user. These sensors emit digital signals via WiFi connection, which will be processed to extract features and, from there, create a data-set of jump activity. With this, it will be possible to analyze the selection of characteristics and measure the performance of these variables using some classification models.

VolleyJump 2.0: A Computational Approach to Analysis and Classification of Volleyball Jumps Based on Multiple Inertial Devices

Currently, there is a big concern of governments and research institutes on evaluating the population awareness about scientific innovations, such as new food-production technologies and the development of drugs. Unmet demand is to find new methods to measure the impact of scientific research and its social outreach. This work presents an Altmetrics-based framework to map the research impacts using alternative metrics based on the exchange of scientific knowledge on social media and online environments. This master thesis contributed to the ZIKAlliance consortium, enabling an online platform to monitor the scientific evolution and its social perception on the Zika epidemic.

REALM: A Framework to Explore Research Impacts by Social Network Analysis, Bibliometrics and Altmetrics

Identifying subjective sentences and classifying the polarity of subjective sentences are two important tasks in sentiment analysis. Besides being a hot topic, there is still a lack of resources to perform the mentioned sentiment analysis tasks in the Portuguese language, with its syntactic specificities. This paper describes the identified challenges and next steps in an initial study regarding the classification of subjectivity and polarity of sentences with a small set of syntactic features extracted directly from the text. Our approach reached satisfying results in experiments with two classic machine learning models in four datasets consisting of user reviews from different domains.

Investigating sets of linguistic features for two sentiment analysis tasks in Brazilian Portuguese web reviews

The Web continues to grow day after day, being the largest source of data in several domains of knowledge. Such a data are particularly available into billions of HTML pages. Due to it, Web scraping is an increasing activity with a great focus on structured data, like Web tables and Web lists. While the literature about extraction and matching of Web tables is extensive, this is not the same for Web lists. The main reason for that is the absence of a heading with fixed and explicit attributes into a Web list, which makes difficult to find out similar data for matching purposes. Related work about Web lists similarity do not deal with the comparison of the content of two different lists. In order to fill this gap, this paper proposes a similarity function for HTML-coded lists called SimList. It innovates by comparing not only the content of the two input lists but also data on the HTML pages that surround the lists and may contribute to infer their contexts. Besides, SimList may be customized by the user in terms of weights for the internal and surrounding data, as well as auxiliary text similarity measures. Preliminary experimental evaluations show that our similarity function had obtained good precision, recall and f-measure scores even considering the inherent heterogeneity of HTML lists on the Web.

A Similarity Function for HTML Lists

Big companies usually have human and financial resources to personalize their websites. On the other hand, small and medium-sized companies usually do not have such resources. In this paper we propose ALARM: A Light Application for Recommendation and Monitoring. This free platform enables automatic recommendations and monitoring in small and medium-sized websites. The platform is independent of the site structure, as well as monitoring and recommendation methods which may be used in it. We illustrate the features of the platform in a case study, where we show how it can be used to provide recommendations as well as to analyze them.

ALARM: A Light Application for Recommendation and Monitoring

Fake news has been around for a long time. But with the advancement of social media and internet access, fake news has become a bigger problem. Because of the rapid spread in social media and instant messaging applications, fake news can reach more people in less time by directly influencing democratic processes, leveraging security issues that sometimes lead to tragic ends. In order to promote a fast and automated method of fake news identification, in this study, we performed an analysis of false Brazilian news, identifying writing patterns through natural language processing and machine learning.

Downloads

Next from WebMedia 2020

SDO: Simulador de Doenças Oculares

Similar lecture

An Open Multilingual System for Scoring Readability of Wikipedia

.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

SDO: Simulador de Doenças Oculares

Similar lecture

An Open Multilingual System for Scoring Readability of Wikipedia

Downloads