Awesome

NTDS Project: Identifying Spammers on Social Network.

This Github repo contains the code for the project part we did for NTDS class at EPFL.

Folder Structure

The folder structure given below is the exact order for the project steps we did and how you should run them.

Each part we did for the project is separated into notebooks and .py script files.

• Network Discovery and Analysis
  • Network_Discovery_and_Analysis.ipynb :
    Network Discovery and Analysis notebook that looks for basic network statistics and explore the network data.
  • DataProcessing.py :
    Data Processing codes needed for the creation of the network for analysis.
• Data Visualization with Gephi
  • Gephi.ipynb : This notebook contains code for creation of the graph in gepx format to be extracted and shown on Gephi.
• Classification
  • Classification.ipynb : Creation of an artifical neural network for spammer classification. (Succesful result)
  • Classification_Spectral_Decomposition(unsuccessful) folder:
    • Neural Net.ipynb,
    • Preprocessing.ipynb,
    • Spectral Decomposition.ipynb :
      Spammer Classification through Spectral Decompostion (Unsecfull attempt)