EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

A more advanced group polarization measurement approach based on LLM-based agents and graphs

Zixin Liu, Ji Zhang, Yiran Ding

Information Research an international electronic journal · 11.03.2025 · 30 (iConf) · 93-107

DOI: 10.47989/ir30iconf47578 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information Research an international electronic journal, online erschienen am 11.03.2025. Verfasst von Zixin Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Group polarization is an important research direction in social media content analysis, attracting many researchers to explore this field. Therefore, how to effectively measure group polarization has become a critical topic. Measuring group polarization on social media presents several challenges that have not yet been addressed by existing solutions. First, social media group polarization measurement involves processing vast amounts of text, which poses a significant challenge for information extraction. Second, social media texts often contain hard-to-understand content, including sarcasm, emojis, and internet slang. Additionally, group polarization research focuses on holistic analysis, while texts is typically fragmented. These challenges indicate that a new solution needs to be proposed.

Method

To address these challenges, we designed a solution based on a multi-agent system and used a graph-structured community sentiment network (CSN) to represent polarization states. Furthermore, we developed a metric called community opposition index (COI) based on the CSN to quantify polarization. Experiments & Conclusion. We tested our multi-agent system through a zero-shot stance detection task and achieved outstanding results, which proved its significant value in terms of usability and accuracy.

Zitieren

APA

Liu, Z., Zhang, J., & Ding, Y. (2025). A more advanced group polarization measurement approach based on LLM-based agents and graphs. Information Research an international electronic journal, 30(iConf), 93-107. https://doi.org/10.47989/ir30iconf47578

Vancouver

Liu Z, Zhang J, Ding Y. A more advanced group polarization measurement approach based on LLM-based agents and graphs. Information Research an international electronic journal. 2025;30(iConf):93-107. doi:10.47989/ir30iconf47578

BibTeX
@article{Liu2025,
  author = {Liu, Zixin and Zhang, Ji and Ding, Yiran},
  title = {A more advanced group polarization measurement approach based on LLM-based agents and graphs},
  journal = {Information Research an international electronic journal},
  year = {2025},
  volume = {30},
  number = {iConf},
  pages = {93--107},
  doi = {10.47989/ir30iconf47578}
}
Kostenlos starten →