A machine learning project on the factors that influence the number of Twitter retweets.
By : Bowei Zhang and Jingxin Zhu
This is a coursework project for Machine Learning and Computational Statistics at NYU, Spring 2014.
Basically we will crawl tweets from celebrities on Twitter. The list of celebrities is provided by Twitaholic, and we are using Twitter API wrapper, namely tweepy for crawling.
You can run the code if you like. We are using Python and the following libraries are neccessary to PERFECTLY run the ENTIRE project:
- NumPy and SciPy
- scikit-learn
- BeautifulSoup
- matplotlib