84728

Автор(ы): 

Автор(ов): 

4

Параметры публикации

Тип публикации: 

Доклад

Название: 

Machine Learning for Meta-opinion Prediction in Social Systems Using Compact Belief Representations

ISBN/ISSN: 

978-3-032-23219-9

DOI: 

10.1007/978-3-032-23219-9_26

Наименование конференции: 

  • International Conference on Artificial Intelligence and Networks (ICAIN 2025)

Наименование источника: 

  • Proceedings of International Conference on Artificial Intelligence and Networks (ICAIN 2025)

Город: 

  • Dubai

Издательство: 

  • Springer

Год издания: 

2026

Страницы: 

344-356
Аннотация
Today, a crucial question in automated opinion mining is the search for consensus and patterns of its formation within public dialogue and deliberation. In our earlier works, we explored the turn of diverse individual opinions into shared meta-opinions. This paper continues the investigation of meta-opinions and examines the properties of their approximations, with particular attention to methods partially grounded in bisimulation contraction and other epistemic logical frameworks of the Kripke type. Research gap is significant complexity to find such a minimal model that is capable of representing possible worlds and the relations among them. We generated heuristics using LLM and measured metrics of this algorithm up to the fifth modal depth. The metrics shown larger than 90% accuracy even for arbitrary initial models.

Библиографическая ссылка: 

Леонова Ю.С., Федянин Д.Н., Рыбаков Д.А., Бодрунова С.С. Machine Learning for Meta-opinion Prediction in Social Systems Using Compact Belief Representations / Proceedings of International Conference on Artificial Intelligence and Networks (ICAIN 2025). Dubai: Springer, 2026. С. 344-356.