Skip to content

Project repository : Virality prediction in social networks.

Notifications You must be signed in to change notification settings

dvp-tran/Statistical_Graph

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

65 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Statistical_Graph : Virality prediction in social networks


Context and motivations:

Virality is, in social networks, an important issue for corporations, political campaigns and influencers as they spend enormous resources and efforts to make their products or messages go viral in order to catch attention and spread their influence/activities to a wider audience. Thus, understanding the complex mechanism of virality may help one control its effects over the network:

  • How does the network structure affect the diffusion?
  • How to model the contagion, etc.

Proposal brought by the paper : the broad idea is that network communities allow predict virality by its early spreading pattern. A simple, popular approach in studying hashtags diffusion is to consider hashtags as diseases and apply epidemic models. However, recent studies demonstrate that diseases and behaviors spread differently. We can see huge potentiality for applications in social media marketing : social networks could give better advice to their users as to which posts are likely to give best advertising Return on Investment.

Project phase:

In order to navigate, please check the notebooks in the notebooks/Python folder. The notebooks are named in order:

  • Hashtags analysis
  • Graph analysis
  • Propagation modeling
  • Features extraction
  • Machine Learning for prediction

A short report summarize all the work in the report folder.

About

Project repository : Virality prediction in social networks.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published