According to the WSJ, Wall Street has a growing desire to find different data – such as social media posts – that can help improve investment decision making, to make predictions about the movements of stocks and other securities and derivatives.
Many sentiment-analysis startups scan Twitter and other social media, but the ability to analyse posts to identify subtle trends is still in development. Social media can provide a useful signal to investors but generally shouldn’t be relied on as the sole reason to make an investment.
Used techniques
There are different techniques to drive market insights:
- Break down sentences into their key components and analyse adjectives and actions associated with subjects mentioned in tweets, as well as their location in sentences, among other factors.
- Identify situations where a person may convey both a negative and a positive in a single utterance.
- Examine not only the meaning of words but also their arrangement in relation to each other.
Twitter Inc. itself also sells data directly to a range of businesses, including hedge funds and banks. Some of those buyers have data scientists who conduct their own analysis of tweets, including of sentiment around companies.
