SNTMNT - Social Media Stock Market Trend Analysis and Prediction

Air-France-KLM

Sentiment Indicator:
Bearish (Confidence 100%)

Sentiment Volume:
0 MSG 1Y AVG (0)

Key Features

Machine learning algorithm that generates an indicator predicting share price movement between 1 and 7 days in the future with an accuracy of 56 percent.

NLP analysis with over 80 percent accuracy in defining mood states.

10,000 sources including Twitter, Facebook and leading news Websites and Blogs.

Engineered based on Academic Research

Bollen, et al, (2010) show that a correlation exists between online sentiment and the Dow Jones Industry Average.

Sprenger and Welpe (2010) find sentiment of tweets to be associated with abnormal stock returns for the S&P 100.

Van Leeuwen (2011) finds correlation for specific "mood states" between online sentiment and the Dutch AEX.

AEX Sentiment and Volume

Online AEX Sentiment

The correlation between online sentiment and stock market movement is an explanatory area of research and our key metric. We strive to visualize this correlation as clear as possible. Therefore, we use this sentiment graph to plot our early sentiment indicator against real AEX Index statistics acquired through Yahoo Finance.

Online Sentiment Volume (Construct)

We use over 10,000 sources including Twitter, Facebook and leading news Websites / Blogs to determine the emotion of online news. Together with Clip It, we divide the entire dataset into five different mood states: very positive, positive, neutral, negative, and very negative. The volume graph gives you not only insight into total sentiment volume, but also into corresponding mood construct.

Social Media Stock Market Trend Analysis and Prediction