Stock Market Prediction using Twitter Sentimental Analysis

Abstract

Now a days, social media perfectly represent the public
sentiment and opinion about current events. For overall population,
predicting stock market movements is an outstanding region of
interest. Uncommonly, Twitter has attracted a lot of attention for
studying and using the public sentiments. Stock market prediction
based on open conclusions communicated on Twitter has been an
interesting field of research and henceforth the basis for different
ideas. It is concluded that public opinion gathered from Twitter and
the actual values likely could be associated . In this system, we have
utilized three unique utilities: Quandl, Twitter and Support Vector
machine (SVM) algorithm for gathering actual value and tweets
through training machine. Here we have utilized sentiment analysis
and supervised machine learning standards to the tweets separated
from Twitter and break down the relationship between stock prices of
an organization and opinions expressed through tweets. At the end of
the paper a detailed analysis showing a strong correlation between
the ascent and descent in stock prices with the public sentiments in
tweets result a nearly accurate dataset which is useful for public.