In this project, I apply natural language processing techniques to understand the sentiment in the latest news articles featuring Bitcoin and Ethereum. I also apply fundamental NLP techniques to better understand the other factors involved with the coin prices such as common words and phrases and organizations and entities mentioned in the articles. In notebook is comprised of three parts:
- Sentiment Analysis
Here I use the News API to pull the latest news articles for Bitcoin and Ethereum and create a DataFrame of sentiment scores for each coin.
- Natural Language Processing
In this section, I use NLTK and Python to tokenize the text in the news articles for for Bitcoin and Ethereum. I then analyse the NGrams and word frequency for each coin. And finally, I generate word clouds for each coin to summarize the news for each coin.
- Named Entity Recognition
In this part, I build a named entity recognition model for both Bitcoin and Ethereum and then visualize the tags using SpaCy.