We are pleased to announce a new peer-reviewed publication by Ljubiša Bojić, co-authored with Velibor Ilić, Veljko Prodanović, and Vuk Vuković, published in Chinese Political Science Review.

The paper introduces the Recommender Systems LLMs Playground (RecSysLLMsP), an agent-based simulation framework designed to study how recommender systems and large language models jointly shape engagement, emotional dynamics, and polarization in social media environments.

The study models a synthetic social media ecosystem with 100 agents grounded in real psychometric and demographic data. Agents interact through feeds with progressively increasing levels of personalization, while content is generated and adapted using large language models. This setup enables controlled observation of how algorithmic personalization affects collective behavior.

Key findings show that moderate personalization maximizes engagement, while full personalization significantly reduces content diversity and amplifies both structural and affective polarization. Network modularity increases sharply as personalization deepens, indicating the emergence of echo-chamber dynamics. At the same time, the simulation demonstrates that LLM-based agents can reproduce realistic patterns of emotional contagion and ideological clustering.

RecSysLLMsP provides a transparent and reproducible “digital laboratory” for testing recommender system designs and policy interventions before they are deployed at scale. The framework has direct relevance for research in computational social science, responsible AI, platform governance, and democratic communication.

Publication details:
An Agent-Based Simulation of Politicized Topics Using Large Language Models: Algorithmic Personalization and Polarization on Social Media
Chinese Political Science Review
DOI: 10.1007/s41111-025-00326-x

In the past weeks, our TWON researcher Fabio Sartori (KIT) and his colleagues worked on a new demonstrator tool to make the dynamics of Online Social Networks tangible for the broad public. The result is: TWONderland!

In our simulation TWONderland, we assign the user the job as the lead designer of a new Online Social Network. In a playful and interactive way, users explore how as the platform designer, they influence the interaction on the platform and how even the tiniest design choices can ripple out to shape behavior, sentiments and relationships between the users – and potentially spark fragmentation and fuel polarization.

Unique about this demonstrator is the step-by-step walkthrough of the functionalities of Online Social Networks (OSNs). The user starts by assigning moods – from aggressive to calm – to fictive platform users. We then visualize how their fictive users are connected to each other on the platform, and how their moods adapt as they are confronted with posts of each other. In TWONderland, every OSN user participates within a specific sentiment corridor, meaning that they will interact with and adapt to other users as long as their differences in sentiment are not too significant. Here, for instance, a very calm user would not immediately interact with somebody who is very aggressive. However, in our demonstrator, we visualize that the sentiment on a platform can still shift in positive and negative directions gradually. These network dynamics were modelled based on the Axelrod model (for further information and technicalities please refer to our Deliverable).

After getting an understanding of network dynamics, the user is asked to experiment with alternative platform mechanisms that determine what users (and their moods) influence their own fictive platform user. Based on the ranking algorithms the user sets, posts with different moods – again, aggressive to calm – will become visible to their fictive character, which influence their mood. From this individual level, the demonstrator then moves on to visualizing bigger networks in which many users influence each other based on the designated platform mechanics. To understand how users influence each other’s mood on OSNs, the user can run comparative simulations and experiment how polarization is fueled or minimized only through the ranking mechanics.

We are proud to announce that our researcher Simon Münker published a new paper with the title: Fingerprinting LLMs through Survey Item Factor Correlation: A Case Study on Humor Style Questionnaire. It is published in the Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing and the results will be presented in Shanghai on 5 November.

LLMs increasingly engage with psychological instruments, yet how they represent constructs internally remains poorly understood. Simon Münker introduces a novel approach to “fingerprinting” LLMs through their factor correlation patterns on standardized psychological assessments to deepen the understanding of LLMs constructs representation. Using the Humor Style Questionnaire as a case study, he analyzes how six LLMs represent and correlate humor-related constructs to survey participants. His results show that they exhibit little similarity to human response patterns. In contrast, participants’ subsamples demonstrate remarkably high internal consistency. Exploratory graph analysis further confirms that no LLM successfully recovers the four constructs of the Humor Style Questionnaire. These findings suggest that despite advances in natural language capabilities, current LLMs represent psychological constructs in fundamentally different ways than humans, questioning the validity of application as human simulacra.