Stefan Scholz

Stefan is coordinator of the centre. While he is working at the centre, he is pursing his PhD with a focus on machine learning, image analysis and social and political event analysis.

📍 Konstanz

Project

Seeing is Deceiving? AI-Manipulated Images and Protest Size Estimates

This project examines the effect of AI-modified images on public perception by examining the effect of manipulated protest images on estimated crowd sizes.

Project

Predicting Protest Escalation by Exploiting Short-Term Dynamics

A prediction framework to predict the dynamics of protest using protest images from social media. The measurement of the protest characteristics per hour also allows us to predict the protest dynamics for the hours and days to follow.

Project

Protest Image Dataset

The Protest Image Dataset is a new data collection project that includes images from social media with an emphasis on political protests. The dataset contains, besides the images themselves, variables on location, time, as well as a hand-annotated protest variable.

Project

Transparent Two-level Classification Method for Images

We present a new method that makes the classification of images more transparent.

Project

Self-Portrayal of Leaders on Social Media

Social media platforms allow leaders to raise their profiles and directly communicate with citizens. The incentives for leaders to visually presenting themselves still differ.

Project

Wickedonna

Two activists reported in the Wickedonna blog about protests in China. They collected social media posts for over 74,000 protest events containing images of the protesters, security forces, banners and more. We will improve the prediction of protest in images by using the images from this blog.