From What-If Scenarios to Event Associations: A Novel Approach to Social Media Event Analysis

Aigerim Mussina, Sanzhar Aubakirov, Paulo Trigo, Madina Mansurova

2025

Abstract

This paper introduces a novel approach to event prediction in social media by applying association rules to generate counterfactual what-if scenarios. Using the Events2012 dataset as a foundation, we developed the EventsAssociation2012 dataset to systematically identify patterns within event sequences and assess the predictive power of what-if scenarios. Employing a Large Language Model (LLM) to generate event embeddings, similarity scores, and conditional probabilities, we mapped real-world scenarios to intra-event and inter-event associations, thereby creating a robust framework for understanding the interconnected nature of social media discussions. Our methodology leverages association rule mining to model causal relationships between events, enabling predictions of plausible future outcomes based on hypothetical scenarios. The results demonstrate the potential for applying what-if scenarios to new event datasets, revealing challenges and opportunities for refining this approach. The study further discusses areas for improvement, such as expanding the identification of intra-event scenarios, exploring multi-event associations, and enhancing topic embedding techniques. Overall, this work advances counterfactual analysis in event prediction, providing a more accurate and comprehensive method for modeling event associations in the dynamic landscape of social media.

Paper Citation

in Harvard Style

Mussina A., Aubakirov S., Trigo P. and Mansurova M. (2025). From What-If Scenarios to Event Associations: A Novel Approach to Social Media Event Analysis. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 203-212. DOI: 10.5220/0013645900003967

in Bibtex Style

@conference{data25,
author={Aigerim Mussina and Sanzhar Aubakirov and Paulo Trigo and Madina Mansurova},
title={From What-If Scenarios to Event Associations: A Novel Approach to Social Media Event Analysis},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={203-212},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013645900003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - From What-If Scenarios to Event Associations: A Novel Approach to Social Media Event Analysis
SN - 978-989-758-758-0
AU - Mussina A.
AU - Aubakirov S.
AU - Trigo P.
AU - Mansurova M.
PY - 2025
SP - 203
EP - 212
DO - 10.5220/0013645900003967
PB - SciTePress