RECENT ASSIGNMENT

Please do it in pycharm
Exercise 8: Analyze news
Assignment Specification
Description: This program will read a pre-processed set of news and extract information about their content.
The dataset. News_2021.csv contains 769 rows composed by:
• title
• link
• keywords
• creator video_url
• description
• content
• pubDate
• full_description
• image_url
• source_id.
News have been collected during the period 10/24/21 and 10/26/21 and they are primarily related to COVID-19.
Input: No user provided input. Data will be from the file News_2021.csv
Output:
1. Print the 20 most common words
2. Print the articles related to COVID-19 and calculate their percentage of the total
3. Print the sentiment for the articles NOT related to COVID-19
4. Print the sentiment for ALL the articles
5. Create a wordcloud with the words in the articles NOT related to COVID-19
6. Create a wordcloud with the words in ALL the articles
See details in the Procedure.
Procedure:
1. Read the input file into a list
2. Text is in either/or -description- or -content-: merge the 2 columns and create a list with all the text
3. Clean the text by:
a. removing stopwords using the file stopwords_en.txt
b. remove non alphabetical words and characters
c. remove punctuation
d. remove words smaller than 3 characters
e. remove URLs
4. Perform the analysis required as -Output-.
Please note: in order to be considered -related to COVID-19-, the article should contain any of the following words: covid, coronavirus, vaccine, vaccination, antibody, moderna, pfizer, johnson