UCD technology to mine more than 300k articles and 4 million blog posts a day

2 Dec 2009

Technology developed at UCD’s School of Computer Science and Informatics will be used to power one of the most powerful media intelligence tools on the planet, and will mine its way through 300,000 news articles and 4 million blog posts on a daily basis.

Polecat, a market-intelligence provider based in Dublin and in the UK, has signed an exclusive, worldwide licence for advanced software algorithms developed by UCD researchers to enhance its strategic market-intelligence platform.

About the licensing

The technology licensed by Polecat arises from a research programme funded by Science Foundation Ireland at UCD’s School of Computer Science and Informatics. The licensing deal was negotiated by NovaUCD, the Innovation and Technology Transfer Centre and Beauchamps Solicitors, the Dublin-based legal firm.

Polecat’s MeaningMine platform analyses statistical and linguistic trends in publicly available digital and broadcast media by mining 300,000 articles and 4 million blog posts daily.

Using a combination of data mining and text analytics, Polecat can extract dominant themes and emerging trends which enables its clients to be informed, monitor and report on the value of their strategic and communication activities.

Polecat’s MeaningMine platform is part of a new market category of advanced software analytics which, according to Forrester, will fuel year-on-year growth in the business intelligence software market to an estimated US$14 billion worldwide by 2014.

According to IDC, the advanced software analytics market represents about 20pc of the overall business intelligence tools market and grew by 12pc in 2008.

What Polecat does

Using its current platform, Polecat can provide clients with insight into emerging trends, influencer networks, competitive analysis and dominant discussions empowering senior organisational strategists to keep up to date with relevant market-intelligence data.

As Polecat’s mining of digital and broadcast media grows and develops, the software tools licensed from UCD, combined with its current technology, will enable it to offer faster and more dynamic market-intelligence information to worldwide businesses and global organisations.

“We are very pleased to be working with University College Dublin,” said James Lawn, Polecat’s chief executive and co-founder.

“It is a highly innovative university and, thanks to this partnership, we believe businesses and Government organisations around the world will soon be able to have truly reliable, measurable and live market intelligence available at their fingertips.”

The advanced software algorithms, or machine-learning technologies, developed by Prof Pádraig Cunningham and Dr Derek Greene, researchers in UCD’s School of Computer Science and Informatics, are based upon “unsupervised learning” algorithms, which enable smarter and faster ways to collect and analyse vast amounts of online data from which meaningful knowledge can be extracted.

If there is a huge amount of data …

This technology has particular applications where there are enormous amounts of data to be extracted and analysed from “noisy” sources, such as the internet and internal organisation networks.

“The collaboration with Polecat is very valuable to us as their experience in market intelligence will inform us about the technology requirements and research challenges in this area,” explained Cunningham, UCD Professor of Knowledge and Data Engineering.

“Research progress in this area requires collaboration between business experts and technologists in order to direct research to address real business requirements.”


Dr François Pichot, NovaUCD, technology transfer team, said that the licensing deal was significant for UCD on several levels.

“Information overload is now a well-known problem in the current data-rich environment, and is not likely to diminish. UCD has licensed advanced software tools to Polecat, enabling meaningful knowledge to be extracted from vast amounts of data.

“This is an exciting space, one which UCD is motivated to see flourish and is all the more relevant in the context of the development of a Smart Economy.”

Polecat, founded in 2007 by James Lawn and Bronwyn Kunhardt, will continue to work with UCD to further develop this technology.

By John Kennedy

Photo: Polecat online.

John Kennedy is a journalist who served as editor of Silicon Republic for 17 years