In this project, we analysis the political news between 2018-07-01 and 2018-12-31 from various media.

The code is written in Python3 with jupyter notebook.

Download the repository

$ git clone https://github.com/MiccWan/Political-News-Analysis.git

Since plotly is used in our project, you need to set your credentials to use the package:

$ python

then in python interactive shell,

>> import plotly 
>> plotly.tools.set_credentials_file(username='<YOUR_ACCOUNT>', api_key='<YOUR_API_KEY>')

• In crawler, we use requests and BeaufifulSoup4.
• In text mining, we use pandas, jieba, sklearn and mlxtend.
• In visualiztion, we use networkx and plotly.

The dataset obtained by crawler is available at this Google Drive Folder.

• /crawler: Crawlers for new_talk and liberty_times.
• /data: Storing the list of events, people and reputation data for future analysis.
• /final_demo: Report and data for final demo.
• /jieba_data: Some dictionary for term frequency analysis.
• /politicians: Images and wordcloud of politicians.
• /tools: Some tools, modules and test file created in analysing.