Skip to content

Latest commit

 

History

History
32 lines (22 loc) · 1.26 KB

README.md

File metadata and controls

32 lines (22 loc) · 1.26 KB
Raw

Stock Sentiment Analysis using News Headlines

Sentiment Analysis is the process of determining whether a piece of writing is positive, negative or neutral. A sentiment analysis system for text analysis combines natural language processing (NLP) and machine learning techniques to assign weighted sentiment scores to the entities, topics, themes and categories within a sentence or a phrase.

In today's communications and news consumption, the headlines of various articles play an even more important role than before. Now, we use sentiment analysis on the headlines of a particular company or companies to determine the effects of the headlines on the stock market. In this project, I used the stock news headline dataset to calculate the sentiment against binary class.

Dataset

(https://www.kaggle.com/geminikeggler/stock-sentiment-analysis)

Project Highlights

  • Load the data
  • Preprocess text data
  • Build and trainthe Model
  • Evaluate the model against the test set

Embedding

  • Bage of Words
  • TFIDF
  • Word2Vec

Models used

  • Random Forest
  • LSTM
  • Ensemble Models
    • Decision Tree

How to Run The Code

All the code and comments are listed in the jupyter notbook (Stock Sentiment Analysis using News Headlines .ipynb)