Skip to content
This repository has been archived by the owner on Aug 19, 2020. It is now read-only.

[NOT MAINTAINED] Predicting Bit coin price using Time series analysis and sentiment analysis of tweets on bitcoin

Notifications You must be signed in to change notification settings

harishpuvvada/BitCoin-Value-Predictor

Repository files navigation

BitCoin-Value-Predictor

Abstract:

The project attempts to predict the future value of Bitcoins by identifying the correlation between social media sentiment and market sentiment. We will achieve this by collecting user feeds from social media such as twitter, facebook and linkedin. Once we have our corpus we will map their associated sentiments using IBM Watson’s Natural Language Understanding API. While mapping sentiments to our corpus we attempt to capture granular level categories namely joy, anger, happiness, etc. We use these as feature vectors to our ML/DL algorithms. Then we compare the results of the different algorithms and choose the one with the best accuracy score.

Technologies:

  • Programming Languages: Python, Java
  • Big data technologies: Spark ML, Spark-SQL, Hadoop Mapreduce
  • Libraries: Pandas, Matplotlib, Scikit-learn, TensorFlow , Keras

Data Sources:

  1. Twitter Api to get the tweets about BitCoins/Cryptocurrencies.
  2. LinkedIn Api to get the corpus on blogs.
  3. Web Scraping to get data from News articles.

Dropbox link with data:

https://www.dropbox.com/s/oy5zcf4aiorr0dr/Archive.zip?dl=0

References:

About

[NOT MAINTAINED] Predicting Bit coin price using Time series analysis and sentiment analysis of tweets on bitcoin

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 4

  •  
  •  
  •  
  •  

Languages