No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.

Lysander: Finding political journalists on Twitter


This directory contains software developed in the pilot of the project Automated Analysis of Online Behaviour on Social Media, a cooperation of the University of Groningen and the Netherlands eScience Center. The main project software repository is called machine learning.

The goal of the project is to analyze tweets of politicians and political journalists. Names of relevant politicians can be collected from documents like parliament member lists and ballots but it is much harder to find the names of relevant journalists. The software in this directory aims to find such journalists by examining the follower links between politicians and other users on Twitter.


Run like:

python markrutte sybrandbuma apechtold > getFollowers.out 

to collect the people that are followed by the users in your seed list. The script needs your Twitter account data to be stored in a file in the format:

# authentication keys
token = "???"
token_secret = "???"
consumer_key = "???"
consumer_secret = "???"

Replace the strings "???" with the key information from , see for instructions

In order to find more relevant users, you can run this command after is finished:

python markrutte sybrandbuma apechtold < getFollowers.out > makevec.out 2> makevec.err

It generates a selection of relevant users (makevec.err) and a vector representations for these users (makevec.out)

Input data files for Dutch politicians can be requested from Erik Tjong Kim Sang