• 25 Jun 2012

Thomson Reuters Adds Psychological Analysis to Machine Readable News

Thomson Reuters MarketPsych Indices identify human emotion and sentiment in news and social media posts to influence and support investment and trading strategies

New York, London, June 25, 2012 - Thomson Reuters today expanded its news analytics service to include a new psychological analysis capability that gauges market sentiment by analysing human emotion in news and social media in order to influence and support investment and trading strategies in financial markets. Thomson Reuters is now offering multi-dimensional psychological analysis for machine readable news, including emotion and sentiment associated with specific countries, commodities, currencies and economic sectors.

Thomson Reuters MarketPsych Indices (TRMIs) provide easy-to-interpret real-time psychological analysis of news and social media. Users can view and model the impact of investor psychology across global asset classes and regions by analyzing the specific attitudes expressed within stories and tracking the macroeconomic themes that are most relevant to price movements in each asset class. This detail level of interpretation helps users to answer in-depth questions with quantifiable evidence to support specific hypotheses in a way not previously possible.

“Questions that are challenging to address can be answered directly using our MarketPsych Indicators and easily incorporated into investment and trading models. Questions like: ‘Are there growing concerns over the stability of the Yuan’s peg to the dollar, and what does this mean for the value of the currency?’ or ‘Is the threat of violence and conflict in Iran heightening or abating, and what does that mean for global oil prices?’,” said Rich Brown, head of quantitative and event driven trading solutions at Thomson Reuters. “This new capability can be used to identify economic sector activity, asset prices, social trends and develop under-the-radar investment hypotheses.”

Developed in conjunction with MarketPsych, a leading consultancy specialising in behavioral economics, TRMIs are delivered to financial institutions as a series of real-time indicators that can easily be incorporated into charting and alerting applications or in quantitative models to help support asset allocation decisions and sector rotation strategies. TRMIs are tailored to specific topics and asset classes and reflect the levels of specific psychological dimensions expressed in news and social media such as optimism, gloom, joy, fear, trust, anger, innovation, violence, conflict, stress, urgency and uncertainty, among others. TRMI also provides a set of metrics on common macroeconomic themes known to influence the prices of commodities and currencies, the growth of economic sectors, and the development of nations. For example, the feed quantifies such items as ‘CropDisease’ for agricultural commodities or ‘CurrencyPegInstability’ for foreign exchange markets.

Thomson Reuters MarketPsych Indices are a natural complement to Thomson Reuters News Analytics (TRNA) as they provide a top-down view of market sentiment from a behavioral finance perspective relating to asset classes, sectors, and countries. When the MarketPsych Indices are used in combination with the news analytics data, users can better understand how the bottom-up signals in TRNA are affected by the psychological states of the market.

Notes to Editors
MarketPsych is a consulting firm that develops financial applications using the latest insights from research in behavioural economics. MarketPsych has extensive experience in identifying signals in data through internally developed statistical software that hones in on the valuable and predictive aspects of this data. By combining this laboratory science with Thomson Reuters software development, the two companies have created language analysis software that extracts psychological meaning from text using natural language processing paired with behavioral economics.

MarketPsych’s text-analysis technology extracts complex meanings from text including such factors as “CropDisease,” “GovernmentAnger”, and “EarningsExpectations.” These concepts are attributed to relevant entities and scored using a patent-pending "meaning-generation" technology, which is a form of natural language processing that identifies the meaning in text by scoring the relationships between key modifier words, significant concepts and entities of attribution. The system’s logic takes into account all of the specific mentions in various news and social media posts and aggregates that data into the specific indices.

About Thomson Reuters
Thomson Reuters is the world's leading source of intelligent information for businesses and professionals. We combine industry expertise with innovative technology to deliver critical information to leading decision makers in the financial and risk, legal, tax and accounting, intellectual property and science and media markets, powered by the world's most trusted news organization. With headquarters in New York and major operations in London and Eagan, Minnesota, Thomson Reuters employs approximately 60,000 people and operates in over 100 countries. Thomson Reuters shares are listed on the Toronto and New York Stock Exchanges.  For more information, go to http://thomsonreuters.com.

Contacts

Kate Reid
PR Director, Trading
Thomson Reuters
Phone: +44 (0) 207 542 2215
Mobile: +44 (0) 7917 200 737
Email

Next Steps

Related Information

More about Machine Readable News