Analysis of Articles Published on Data Science

Jicksy John

Kristin Bässe

Lakshmi Prasannakumar

Data Collection

How we collected the data and more

​

​

​

[1] NEWS API, News API; 07/14/18 accessed; https://newsapi.org/

​

© 2017 Udacity. All rights reserved.

• We collected data using NewsAPI^[1] in Python
• Articles are collected from 16 popular public publishing sources
• Total Articles collected: 9961
• Time Period: 02/20/2018 to 07/14/2018
• Articles are fetched for Data Science, Data Analytics, Machine Learning, Business Analytics and Artificial Intelligence
• Github Link for project code: https://github.com/jicksy/news-analysis
• Findings: General Article Publishing Trend, Top Publishers, Gender Ratio of Authors

2

1. General Article Publishing Trend

​

​

​

​

© 2017 Udacity. All rights reserved.

Graph plotted using Google Spreadsheet

​

​

3

2. Top Publishers Identified

Using Wordcloud^[2] in Python

[2] Adiljadoon-Kaggle, WordCloud with Python; 07/19/18 accessed; https://www.kaggle.com/adiljadoon/word-cloud-with-python

© 2017 Udacity. All rights reserved.

​

• Size of publisher in the image represents the frequency of articles published on the website

→ e.g. Business Insider and Forbes have most articles with data science and related keywords

3. Gender Ratio of Authors

​

© 2017 Udacity. All rights reserved.

​

• We analyzed the top 60 authors and found that there are twice as many male authors than female authors

​

Pie chart created using Google Spreadsheet

​

​

5

Group Photo

© 2017 Udacity. All rights reserved.

6

Kristin Bässe(@Kristin) Lakshmi P (@lakshmi) Jicksy John (@jicksy)