How big data can be used to understand major events

March 04, 2015

With the most unpredictable UK general election looming in modern times, how can big data be used to understand how elections are covered by the media? New research has for the first time analysed over 130,000 online news articles to find out how the 2012 US presidential election played out in the media.

Academics from the University of Bristol's Intelligent Systems Laboratory (ISL), led by Nello Cristianni, Professor of Artificial Intelligence, analysed mass media coverage from the 2012 US presidential election using big data. The paper is published in the journal Big Data and Society.

This is the first study in which political positions have been automatically obtained from a very large amount of online news. The system created goes well beyond traditional word-association networks with the use of richer linguistic analysis of texts.

By analysing the individual campaigns of the main presidential candidates, Obama and Romney, the research team studied how each campaign was represented in the media and found one of the key issues covered by the media during the 2012 campaign was Obama's defence of his record on economic policy.

The findings suggest the issues of the Democratic Party the media focused on were the US economy and civil rights. Overall, media reporting contained more frequent positive statements about the Democrats than the Republicans. The Republicans were also more often the focus of negative statements by Democrats and other players.

The study found the Republicans had more divisive opinions on issues compared to the Democrats. The most contentious subjects in the campaign were the economic split between the two camps of tax breaks and the economy, and the split over gay marriage.

Saatviga Sudhahar, Research Assistant in Machine Learning in the ISL and Department of Computer Science, and the main researcher on the project, said: "Mapping the full electoral campaign coverage by offline and online media is a very difficult challenge, given the large amount of data and the large number of sources available in advanced democracies.

"We believe that the methodology used for the study is a big step forward in the linguistic analysis of texts by using extracted relational data and could help us understand major events."

The research team used a semantic graph that analysed the text and linked it to identified noun phrases and verbs. The subject-verb-object triplets were then used as building blocks for a network. This method has never been applied to a real-world dataset on this scale and millions of documents were analysed to complete the study.

By using media data and having relationships in a graph, the researchers uncovered a unique mixture of endorsements and disapproval to represent the Republican and Democratic camps.

The research team found that the range of political positions can be reliably recovered from the set of claims attributed to each actor by the media reporting. The split of the network into the two main camps provides strong evidence that the main political relations can be found by using this approach.
-end-
Paper:

'Automated analysis of the US presidential elections using big data and network analysis' by Sudhahar S, Veltri GA and Cristianini N in Big Data and Society.

Further information about the study, together with together with high-res images, is available at http://mediapatterns.enm.bris.ac.uk/USElections

University of Bristol

Related Big Data Articles from Brightsurf:

Predicting sports performance with "big data"
Smartphones and wearable devices are not simple accessories for athletes.

Big data could yield big discoveries in archaeology, Brown scholar says
Parker VanValkenburgh, an assistant professor of anthropology, curated a journal issue that explores the opportunities and challenges big data could bring to the field of archaeology.

Army develops big data approach to neuroscience
A big data approach to neuroscience promises to significantly improve our understanding of the relationship between brain activity and performance.

'Big data' for life sciences
Scientists have produced a co-regulation map of the human proteome, which was able to capture relationships between proteins that do not physically interact or co-localize.

Molecular big data, a new weapon for medicine
Being able to visualize the transmission of a virus in real-time during an outbreak, or to better adapt cancer treatment on the basis of the mutations present in a tumor's individual cells are only two examples of what molecular Big Data can bring to medicine and health globally.

Big data says food is too sweet
New research from the Monell Center analyzed nearly 400,000 food reviews posted by Amazon customers to gain real-world insight into the food choices that people make.

Querying big data just got universal
A universal query engine for big data that works across computing platforms could accelerate analytics research.

What 'Big Data' reveals about the diversity of species
'Big data' and large-scale analyses are critical for biodiversity research to find out how animal and plant species are distributed worldwide and how ecosystems function.

Big data takes aim at a big human problem
A James Cook University scientist is part of an international team that's used new 'big data' analysis to achieve a major advance in understanding neurological disorders such as Epilepsy, Alzheimer's and Parkinson's disease.

Small babies, big data
The first week of a newborn's life is a time of rapid biological change as the baby adapts to living outside the womb, suddenly exposed to new bacteria and viruses.

Read More: Big Data News and Big Data Current Events
Brightsurf.com is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to Amazon.com.