bbiyongel / analysis-of-news-popularity-time-series Goto Github PK

This the final project of 553.636 Data Mining, 2018 Fall.

We are trying to figure out impacts of news to be popluar concerning both peak and longevity. Find report here: https://github.com/DanieljcFan/Analysis-of-News-popularity-time-series/blob/master/Data-Mining-final-project-fall-2018.pdf 

The dataset is from UCI machine learning repository. Orginal link: http://archive.ics.uci.edu/ml/datasets/News+Popularity+in+Multiple+Social+Media+Platforms#

For simplicity we analyzed only a subset of orginal data:
sub_news.csv
sub_facebook.csv
sub_google.csv
sub_linkedin.csv

***please note that every news appears in all platforms 
different topics in same platforms are merged

Orgnial File:
News_Final.csv
Facebook_Economy.csv
Facebook_Microsoft.csv
Facebook_Obama.csv
Facebook_Palestine.csv
GooglePlus_Economy.csv
GooglePlus_Microsoft.csv
GooglePlus_Obama.csv
GooglePlus_Palestine.csv
LinkedIn_Economy.csv
LinkedIn_Microsoft.csv
LinkedIn_Obama.csv
LinkedIn_Palestine.csv