Sign in

Automated Analysis of Online Behaviour on Social Media

Gaining insights in the use of Twitter by politicians and journalists

Image: European Parliament (flickrCC)

This project applies machine learning to study a) discursive practices of politicians and journalists on Twitter, and b) to what extent institutional differences between agents still matter, or even exist, now they have similar publishing opportunities on social media. While automated analysis of the content of tweets is intensively studied, the project’s focus on behaviour is innovative. It aims to develop a tool for large-scale automated content analysis of latent categories of behavior that should be scalable in terms of big data sets and various social media platforms.

The project builds upon previous work by the research team in which manual content analysis was applied to study discursive practices of politicians and journalists. A detailed coding scheme was designed to code latent categories of online behaviour (or: discursive practices) such as broadcasting, promoting, criticizing, branding, requesting input etc. These annotated data sets will be used to train the computer.

Our work suggests that although journalists and politicians have different roles and goals, their behaviour on social media is surprisingly similar. This hypothesized redistribution of power in the so-called “triangle of political communication” calls for a revision of classic theoretical insights that are key to both political communication and journalism studies.

Participating organisations

Social Sciences & Humanities
Netherlands eScience Center
University of Groningen



Finding the Best Training Data for Your Machine Learner with Active Learning

Author(s): Erik Tjong Kim Sang
Published in 2018


Marcel J. Broersma
Principal investigator
University of Groningen
Marc Esteve Del Valle
Rijksuniversiteit Groningen
Erik Tjong Kim Sang
Erik Tjong Kim Sang
eScience Research Engineer
Netherlands eScience Center
Jisk Attema
Jisk Attema
Senior eScience Research Engineer
Netherlands eScience Center

Related projects

Inside the filter bubble

A framework for deep semantic analysis of mobile news consumption traces

Updated 3 months ago


Advancing media history by transparent automatic genre classification

Updated 2 weeks ago


Analysis of social media messages

Updated 3 months ago

Related tools



Retrieve recent tweets from certain users and classify them with machine learning

Updated 2 weeks ago
4 1



Find people on Twitter given a small initial set of interesting people.

Updated 2 weeks ago
1 1