There are almost 65 million brazilians connected to the Internet - 36% of the Brazilian Population, according to Comitê Gestor da Internet no Brasil. As a consequence, events such as the Brazilian Election Running have become popular topics in the Web, mainly in Online Social Networks. Our goal is to understand this new reality and present new ways to watch facts, events and entities on the fly using the Web and user-generated content available in Online Social Networks and Blogs.
The UFMG researchers use a set of new techniques related to Information Recovery, Data Mining and Data Visualization to understand and summarize what the media and users are talking about on the Web. That is the fundamental piece to evaluate the impact of the Olympic Campaigns and how users react to news and discussions. One new feature in this project is the possibility to see the propagation of the Tweets: "We are the first to show how many people were reached by a same information in a timespan" - says Wagner Meira Jr.
The Observatório da Web is a research project part of the Instituto Nacional de Ciência e Tecnologia para a Web, sponsored by CNPq and Fapemig. There are over 30 experts involved in the project, from four differente Federal Universities: Universidade Federal de Minas Gerais (UFMG), Centro Federal de Educação Tecnológica de Minas Gerais (CEFET-MG), Universidade Federal do Amazonas (UFAM) e Universidade Federal do Rio Grande do Sul (UFRGS).
Can someone find out a soccer match's final result just by checking the volume of tweets and posts that mention the two teams and the match? That is possible with a high precision. That is only one of the features offered by the Observatório do Brasileirão.
Besides following the matches of the first division of the Campeonato Brasileiro, the Observatory works ininterruptly to measure the volume of Tweets realated to each team and indicate the most popular videos and links among many other informations.
The Observatório da Dengue is an active epidemiological surveillance system developed with Instituto Nacional de Ciência e Tecnologia em Dengue (INCT em Dengue).
TheObservatório da Dengue is able to collect, analyse and present informations in real time about Dengue from more than a hundred of sources in the internet, including social networks and blogs. The system allows to visualize the collected information from many point of views and provides estimates about the incidence of dengue in specific regions in real time. The estimates are based on the time-space correlation of the dengue incidences between the data collected from the internet and the data gathered from the Ministério de Saúde.
As the Olympic Games go on in London, we collect social data about it from here, Brazil! The Computer Science Department from UFMG decided to take a general view of the Olympic buzz to the public through the Olympics Observatory. This experiment pursues to capture discussions about the event in Online Social Networks, blogs and Web Portals. The results can be acessed in english (observatorio.inweb.org.br/olympics) and portuguese (observatorio.inweb.org.br/olimpiadas).
As Professor Wagner Meira Jr., the Coordinator of the experiment, pointed, one of the challenges of the project is to deal with the european communication patterns that are way different from the brazilians' since the europeans are more "connected": "This is a different scenario from the previous where we have worked in. Europeans uses mobile devices in a larger scale and that shall generate a bigger volume of dicussion in the web about real-time events".
The impact of the project has led it to be invited by the Brazilian Government to be presented at the Braziliam Embassy in London during the Olympics. Along with another 12 national digital projects, it was released on Augusth, 26th - the same day the Olympic Games began.
This multidisciplinary project aimed to show the visibility of the candidate running for the Presidence in 2010 in news websites, blogs and Twitter. Over 200 information sources offered a broad view of the dynamic in the websphere towards each candidate.
Intuitive and interactive features allowed many complementary analysis such as the frequency of citations and classification of news articles by themes. All the references to each candidate are available on the Web and were collected by dozens of softwares developed by the Computer Science Department at UFMG.
For the 2010 World Cup, we developed an intercative website using new technologies to follow news and gather web user-generated content about the 2010 World Cup in real-time. With this pioneering project, we were able to show the visibility of teams and players in blogs, news websites and Twitter during the World Cup.
The special features developed for this project included the ability to show the location of tweets on the World Map. Using key words, we were able to reveal the most referecend images and videos in Twitter.