Reuters Adds Instant Media Analysis to Trading Mix

Global news and information company Reuters has enhanced its machine-readable news service to include analysis of news sentiment, driven by linguistics software created by text analytics firm, Corpora.

The new system will 'read' news articles and score how positive or negative they are. This will allow customers to analyse news across thousands of companies, and will enable trading machines to react to news immediately.

The system works by allocating numerical 'sentiment scores' to words or phrases which then provide an overall positive, neutral or negative score about the subject of the news article. These scores are then added together to calculate the level of sentiment for a company, a sector, an index, or global market.

Peter Moss, Reuters Global Head of Enterprise Solutions said: 'This latest release offers the exciting prospect of allowing machines to interpret the sentiment of news stories as they are published, enabling them to react in an informed way to market events at ultra-high speed. Imagine a machine scanning hundreds of stories on companies' results, measuring the sentiment around them and incorporating that into algorithmic trading strategies. This powerful capability can have a meaningful impact on a client's portfolio performance.'

Mark Thompson, CEO of Corpora says his company is delighted to partner with Reuters to utilise its text analysis expertise. Corpora was founded in 2000 to develop 'Natural Language Processing' based software solutions to improve the way organisations manage and use information. The firm employs 75 staff based in its Surrey headquarters and its offices in Canada and Singapore. Reuters has 16,900 staff in 94 countries, including 2,400 editorial staff in 196 bureaux serving 131 countries. The firms are on the web at www.reuters.com and www.corporasoftware.com .

All articles 2006-23 written and edited by Mel Crowther and/or Nick Thomas, 2024- by Nick Thomas, unless otherwise stated.