Methods

Approaches and techniques for data analysis

This section details the methodological approaches we use in our analyses. From statistical techniques to research design, we believe in transparency about how we derive our insights and the limitations of our methods.

politics: Understanding Germany’s TikTok Landscape

Methods
Political Communication
Social Media
Data

This analysis explores TikTok’s transformative impact on German political discourse through the lens of the 2025 snap election. Following the collapse of Chancellor Scholz’s coalition in November 2024, political parties were forced to rapidly adapt their communication strategies to reach digitally-native youth voters. Our research, drawing on data from Meyer et al. (2024), reveals how the AfD established algorithmic dominance through content volume and emotional messaging, while parties like Die Linke found surprising success through authentic counter-narratives focused on social justice. The study examines content strategies, algorithmic influence, and network structures to illuminate how TikTok’s recommendation systems are reshaping political engagement patterns. Beyond documenting party-specific approaches, this investigation raises critical questions about platform neutrality, information integrity, and the future of democratic processes in an era where political battlegrounds increasingly exist within attention economies.

Apr 1, 2025
Lasse Rodeck
21 min
4,052 words

Simulating Conflict Dynamics in the South China Sea: A Monte Carlo Approach

South China Sea
Conflict simulation
Geopolitical analysis
Data
Methods
The South China Sea has emerged as one of the most contentious geopolitical hotspots of the 21st century, embodying a complex interplay of historical grievances, territorial…
Oct 4, 2024
Lasse Rodeck
59 min
11,792 words

Analyzing Media Coverage of the 2015/2016 Refugee Crisis: What Natural Language Processing Reveals

Methods
Refugee Crisis
Media Analysis
Natural Language Processing
Sentiment Analysis
Political Discourse

This article examines how German media framed the 2015/2016 refugee crisis by applying Natural Language Processing techniques to over 15,000 articles from Bild and Spiegel Online. Using sentiment analysis, topic modeling, and named entity recognition, I reveal a clear decline in sentiment over time, especially after the Cologne New Year’s Eve incidents. The analysis shows how automated text processing can efficiently identify narrative shifts and provide quantitative evidence for media framing theories, while demonstrating the potential of AI-powered methods in political discourse analysis.

Jun 30, 2024
Lasse Rodeck
36 min
7,134 words
No matching items
Back to top

Comments