摘要
The rapid growth of social networks has produced an unprecedented amount of user-generated data, which provides an excellent opportunity for text mining. Sentiment analysis, an important part of text mining, attempts to learn about the authors’ opinion on a text through its content and structure. Such information is particularly valuable for determining the overall opinion of a large number of people. Examples of the usefulness of this are predicting box office sales or stock prices. One of the most accessible sources of user-generated data is Twitter, which makes the majority of its user data freely available through its data access API. In this study we seek to predict a sentiment value for stock related tweets on Twitter, and demonstrate a correlation between this sentiment and the movement of a company’s stock price in a real time streaming environment. Both n-gram and “word2vec” textual representation techniques are used alongside a random forest classification algorithm to predict the sentiment of tweets. These values are then evaluated for correlation between stock prices and Twitter sentiment for that each company. There are significant correlations between price and sentiment for several individual companies. Some companies such as Microsoft and Walmart show strong positive correlation, while others such as Goldman Sachs and Cisco Systems show strong negative correlation. This suggests that consumer facing companies are affected differently than other companies. Overall this appears to be a promising field for future research.
The rapid growth of social networks has produced an unprecedented amount of user-generated data, which provides an excellent opportunity for text mining. Sentiment analysis, an important part of text mining, attempts to learn about the authors’ opinion on a text through its content and structure. Such information is particularly valuable for determining the overall opinion of a large number of people. Examples of the usefulness of this are predicting box office sales or stock prices. One of the most accessible sources of user-generated data is Twitter, which makes the majority of its user data freely available through its data access API. In this study we seek to predict a sentiment value for stock related tweets on Twitter, and demonstrate a correlation between this sentiment and the movement of a company’s stock price in a real time streaming environment. Both n-gram and “word2vec” textual representation techniques are used alongside a random forest classification algorithm to predict the sentiment of tweets. These values are then evaluated for correlation between stock prices and Twitter sentiment for that each company. There are significant correlations between price and sentiment for several individual companies. Some companies such as Microsoft and Walmart show strong positive correlation, while others such as Goldman Sachs and Cisco Systems show strong negative correlation. This suggests that consumer facing companies are affected differently than other companies. Overall this appears to be a promising field for future research.
