Social Alpha: Channeling the Chatter

Social media has been transforming nearly every industry, including financial services. It is also a broad term that captures all types of content, from short and sweet tweets to lengthy and detailed commentaries. While investors have been using social media (think Yahoo! Message Boards) as a part of the decision process for years, the prospects of better social media analytics and automating its incorporation into trading comes at a time when there is an explosion in quantity and types of data, with the likelihood of bigger possibilities.

In the analysis process, the first question is what content should be included. Some techniques include the links inside tweets, which could lead to any number of secondary pieces of content. Once the data has been scrubbed and filtered, the most common type of analysis is sentiment. The most basic form of sentiment is polarity, a negative or positive sentiment. Richer sentiment analysis can include a wide range of emotions, like frustration, fear, or joy. An even more elaborate analysis can go beyond emotions and describe broader macroeconomic themes and concepts such as social unrest and violence.

The sheer number of social analytic start-ups shows how much excitement there is for this concept. However, the trend itself is still in its infancy and there are a variety of obstacles that both vendors and users face. For tweets, there are two key challenges: lack of context and volume. In a comment no more than 140 characters long, identifying sarcasm and other forms of unreliable narration is highly problematic. The volume of the Twitter fire hose amounts to over 430 million tweets each day with peaks of up to 600,000 tweets per minute.

Despite this great quantity of data, there is still a question about its breadth of applicability in the financial services. Social media democratizes broadcast mechanisms that once belonged to traditional media. It opens the door for massive changes in the way that communication spreads and thus how it influences markets. But the field is still burgeoning and there are still improvements to be made. Twitter, in particular, could be interpreted as essentially a massive crowd-sourcing project, with each tweet representing a viable data point. Coalesced, these points can give insight on an array of topics. If one of the requirements of financial decisions is to have the temperature of public opinion, this new source of analytics is the thermometer.