Reuters' NewsScope and Sentiment Analysis are new ways of receiving the financial news (Interest Rates, Consumer Price Indexes, etc.), so that the news can be used in custom indicators and trading systems in real time. According to Reuters, NewsScope and Sentiment Analysis are designed for use in algorithmic trading, where computer programs make all of the trading decisions including the entry and exit of any trades (i.e. fully automated fundamental trading).
NewsScope
In addition to providing the news in written form (i.e. for humans to read), NewsScope also provides the news in a form that can be used by computer programs. The computer readable information consists of metatags (similar to XML) that identify various pieces of information within the news, such as the following :
- Security ID : Identifies the market, such as an individual company, a stock index, or a currency market
- Topic Code : Identifies the type of news, such as an earnings report, or a regulatory approval
- Industry Code : Identifies the industry sector, such as the financial, manufacturing, or technology sectors
- Geographic Code : Identifies the location of the news, such as North America, Europe, or Asia
- News Type : Identifies the type of news release, such as an editorial, or a story
- Additional tags : Aadditional tags that identify other parts of the news
Sentiment Analysis
Where NewsScope provides the news in a computer friendly format, Sentiment Analysis actually reads the news, and decides whether the news is positive or negative. Sentiment Analysis assigns either a positive or negative score to various words (such as strengthening, weakening, approved, denied, etc.), and then counts the occurences of these words in the news release, arriving at a final total that indicates whether the news was positive (because it had a positive score), or negative (because it had a negative score). For example, a news release by the US Central Bank that frequently used the words weak, weakened, and weakening, but only once used the words strength, and strengthen, would have a negative score, and would be interpreted as having a negative influence on the US markets. In addition to deciding whether an individual news release is positive or negative, the scores of each individual news release can be combined into a total score, thereby showing whether the recent news has been positive or negative for a specific company, a particular sector, or a complete stock index.
Reuters' Sentiment Analysis is not the first computer program to read the news and decide whether it is positive or negative. BNP Paribas developed their own indicator that reads the news looking for words that imply strength or weakness, and decides how to trade depending upon the number of times various words are used. Reuters' Sentiment Analysis is the first such system to be available to individual traders, and allows individual traders to day trade using fundamentals in addition to, or instead of, technical analysis.
Real Time and Archived News
NewsScope and Sentiment Analysis are available in real time, so that they can be used by automated trading systems that are trading live or in simulation. They are also available as historical data, so that they can be used to test trading systems on past news, and see what the past performance of a trading system would have been. The format of the real time and historical news are identical, so once an automated trading system has been tested using historical news, it can start trading live without requiring much (if any) modification.
Availability and Further Information
Not all of Reuters' products and services are available in all geographical regions, but both NewsScope and Sentiment Analysis are available in all geographical regions. Both services also cover global news, so traders should be able to use NewsScope and Sentiment Analysis regardless of which markets they trade. Further information about NewsScope and Sentiment Analysis are available at Reuters' web site :
