This repository contains the code for a basic Sentiment Analysis on Financial Blogs I performed as part of my portfolio project at Data Science Retreat (Berlin).
The project goal is to build a model to predict Stock Market prices, using a combination of Machine Learning Algorithms.
The output of the prediction are the daily returns of S&P-500 index.
The idea I had was to combine financial data (Open Price, Adjusted Close Price etc..) with Sentiment Analysis of posts published on specific blogs.
The intuition behind this is that people's ideas and behaviors are strongly affected by what analysist write. Thus, powerful and wide spread blogs can definitely influentiate how investors trade and consequently stock markets.
In the light of what I said I tried to get the 'feeling' of a specific day, computing a 'Sentiment Score' out of blog posts.
The blogs I scraped and analyzed are the following: