activity
20242026
collaborators

9 papers

cs.HC2026

Knowing You Is Everything: LLM Agents Achieve Near-Perfect Profile-Consistent Reaction Prediction in Social Media Simulation

Ljubisa Bojic, Ljiljana Matic, Joerg Matthes +3

Autonomous AI agents in social media present concrete risks to democratic discourse and platform governance, while also offering tools for pre-deployment recommender system testing…

cs.CL2026

LLM Agents Predict Social Media Reactions but Do Not Outperform Text Classifiers: Benchmarking Simulation Accuracy Using 120K+ Personas of 1511 Humans

Ljubisa Bojic, Alexander Felfernig, Bojana Dinic +4

Social media platforms mediate how billions form opinions and engage with public discourse. As autonomous AI agents increasingly participate in these spaces, understanding their be…

cs.CY2025

Towards New Benchmark for AI Alignment & Sentiment Analysis in Socially Important Issues: A Comparative Study of Human and LLMs in the Context of AGI

Ljubisa Bojic, Dylan Seychell, Milan Cabarkapa

As general-purpose artificial intelligence systems become increasingly integrated into society and are used for information seeking, content generation, problem solving, textual an…

cs.CY2025

The Dual Impact of Virtual Reality: Examining the Addictive Potential and Therapeutic Applications of Immersive Media in the Metaverse

Ljubisa Bojic, Joerg Matthes, Agariadne Dwinggo Samala +1

The emergence of the metaverse - envisioned as a hyperreal virtual universe enabling boundless human interaction - has the potential to revolutionize our conception of media. This…

cs.CL2025

Does GPT-4 surpass human performance in linguistic pragmatics?

Ljubisa Bojic, Predrag Kovacevic, Milan Cabarkapa

As Large Language Models (LLMs) become increasingly integrated into everyday life as general purpose multimodal AI systems, their capabilities to simulate human understanding are u…

cs.SI2025

Towards Recommender Systems LLMs Playground (RecSysLLMsP): Exploring Polarization and Engagement in Simulated Social Networks

Ljubisa Bojic, Zorica Dodevska, Yashar Deldjoo +1

Given the exponential advancement in AI technologies and the potential escalation of harmful effects from recommendation systems, it is crucial to simulate and evaluate these effec…