ttb-git / berkeley-final-datacollection-and-eda Goto Github PK

by Tauseef Bashir

With the growth of market capitalization of cryptocurrencies (increased from $17 billion in 2017 to $2.25 trillion in 2021), cryptocurrencies remain incredibly volatile, with their value impacted by a multitude of factors: market trends, politics, technology…and Twitter. There have been instances where their prices were affected by tweets by famous personalities and the general public.

I plan to analyze trends over time, particularly the impact of social media on the price volatility of a crypto asset, such as Bitcoin (BTC).

Research Question: Twitter Sentiment Analysis for Predicting Digital Assets Price Movements

BTC tweets dataset: https://www.kaggle.com/datasets/kaushiksuresh147/bitcoin-tweets

BTC historical data: https://www.kaggle.com/datasets/mczielinski/bitcoin-historical-data

Please see the attached notebooks for setailed graphs and conclusions.

Please find attached the following two notebooks for bitcoin twitter and financial analysis:

• BTC-Twitter-EDA.ipynb
• BTC-analysis-using-Prophet-Pycarat.ipynb

1. Time series prediction using Prophet in Python by Renu Khandelwal
2. Housing pices EDA and Prediction by Ruchi Bhatia
3. 88.9 r2_score with pycaret by Kerem Yucedag
4. Pycaret documentation