TITLE:
Sentiment Analysis of Investor Opinions on Twitter
AUTHORS:
Brian Dickinson, Wei Hu
KEYWORDS:
Sentiment Analysis, Word2vec, Text Mining, Twitter, Stock Prediction
JOURNAL NAME:
Social Networking,
Vol.4 No.3,
July
9,
2015
ABSTRACT: 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.