There has been a lot of talk about bias in the news media but it can be hard to figure out which media is truly biased. This project attempted to create a way of rating bias in news sources. Scrapping 550 articles from the internet, NLTK was used to analyize the words in the news articles which were sepereated into clusters. The clusters were able to correlate with their respective sources.
Link to the presentation is here.
- Pandas
- Numpy
- SKLearn
- Anaconda
- Requests
- BeautifulSoup
- Time
- Selenium
- Pickle
- Matplotlib
- Scipy
- Math
- NLTK
pip install -r requirements.txt
- Open Jupyter notebook through the anaconda navigator and select Project_Fletcher_final
- Open the notebook and select Run All Cells
- IPython_notebooks: Contains the notebooks used to code in Python
- Presentation: Contains a pdf version of the presentation
- IPython_notebooks-Pickle_files: Contains pickled files for the data used