You are here:  Home  >  Data Education  >  BI / Data Science News, Articles, & Education  >  Current Article

Money Hunt: More Semantic and Sentiment Analytics Tools Aim At Stock Market Success

By   /  July 6, 2012  /  1 Comment

Money image via Shutterstock

Turmoil seems to be the default option for worldwide financial markets, but turns out there has been good news on the stocks front. According to a Bloomberg Businessweek article this week, U.S. stocks have had a solid 2012 so far, with the Standard & Poor’s 500 index up 9 percent this year, through Thursday, and Nasdaq up 15 percent. But the article also points out that hundreds of billions of dollars have fled the market here in the last three years.

It’s probably no surprise that skittishness reigns among average Americans, and institutional investors, too, given issues like the continuing economic volatility in Europe and more disappointing U.S. jobs data. But where many see problems, others see opportunities – including a new round of projects and vendors with semantic and sentiment analysis solutions aimed at helping investors ferret out what might be on the market’s minds.

The last couple of weeks alone saw the following unveiled:

  • The EU FIRST (large scale inFormation extraction and Integration infrastructure for SupporTing financial decision making) consortium, which employs artificial intelligence to support financial decision making, launched its first running prototype of a technology that can extract and analyze sentiment about the financial domain from social media networks in near real-time. The prototype, debuted at the ABI Lab Conference in Milan, Italy, analyzes Tweets as well as textual data from blogs, extracting sentiment and relating it to stock price movements. Its online demo, for example, provides a sentiment timeline of positive and negative views of Netflix on Twitter between March and December 2011 and relates them to manually-entered data about events occurring in that timeframe, including its failure to renew its movie deal with Starz in early September that was being closely followed. Sentiment difference was relatively positive for Netflix through the end of August but the prototype shows it making a crossover in early September before Netflix stock took its big price plunge. The demo cheekily notes that more large-scale studies are needed before it can positively relate sentiment to price trend, and “we can all get stinking rich.” Other capabilities of the prototype so far include detecting scenarios of financial market abuse, such as attempts to manipulate prices of financial instruments via false information releases. The consortium also plans to extend the technology’s focus to the identification and handling of reputational risks that can be a “substantial threat to the stability of global financial markets,” it says. The project runs until the fall of 2013.


  • Thomson Reuters is bringing psychological analysis to gauge market sentiment, adding to its News Analytics service the analysis of human emotion and sentiment in news and social media to help support institutional investors’ investment and trading strategies. In a partnership with behavorial economics consultancy MarketPysche, the MarketPsyche Indices draw out from machine-readable news in real-time indicators around “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,” according to a press release. Other metrics include those on common macroeconomic themes known to influence the prices of commodities and currencies, the growth of economic sectors, and the development of nations, it says. “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, in a statement. “This new capability can be used to identify economic sector activity, asset prices, social trends and develop under-the-radar investment hypotheses.”


  • HedgeChatter.com from Skotino Dynamics is a social media stock sentiment trend analytics offering for retail investors that monitors keywords, trends, conversations and social media stock sentiment across social media sites, its goal being both to uncover social media impact on a company’s stock price and also deliver insights into who is influencing the stock’s movement. Influencers, determined by overall volume of postings, how many followers they have, and how accurately they predict stock price movements, can be tracked as well as stocks.


  • SNTMNT, which specializes in natural language processing and text analysis for social media, has released its Trading Indicator API. It says its technology is the first to give hourly and/or daily buy and sell signals for all S&P 500 stocks based on online buzz on Twitter, to deliver predictions of stock price movements with an accuracy as high as 60 percent. Its prediction engine incorporates sentiment analysis using NLP algorithms to classify both by financial and brand sentiment whether the Twitter feed for an S&P500 fund is positive or negative, and also takes into consideration the tweet’s author’s reach and authority. Machine learning techniques provide the correlations between Twitter sentiment, author authority and the S&P 500, and the company claims that predictions that result from these correlations can have an average accuracy of 54 percent. Each prediction is accompanied by a confidence interval that reflects the reliability of the prediction, it says. The company is looking for partners who’d like to include its API in their own models.

About the author

Jennifer Zaino is a New York-based freelance writer specializing in business and technology journalism. She has been an executive editor at leading technology publications, including InformationWeek, where she spearheaded an award-winning news section, and Network Computing, where she helped develop online content strategies including review exclusives and analyst reports. Her freelance credentials include being a regular contributor of original content to The Semantic Web Blog; acting as a contributing writer to RFID Journal; and serving as executive editor at the Smart Architect Smart Enterprise Exchange group. Her work also has appeared in publications and on web sites including EdTech (K-12 and Higher Ed), Ingram Micro Channel Advisor, The CMO Site, and Federal Computer Week.

  • Traders using the tools makes the most out of the volatile markets. Volatility and market crashes mostly affects the small investors only.

You might also like...

Evolving Cloud Networks and How to Keep Them Secure

Read More →