collaborators

6 papers

cs.CL2026

Large Language Models for Causal Relations Extraction in Social Media: A Validation Framework for Disaster Intelligence

Ujun Jeong, Saketh Vishnubhatla, Bohan Jiang +3

During disasters, extracting causal relations from social media can strengthen situational awareness by identifying factors linked to casualties, physical damage, infrastructure di…

cs.LG2025

CAMO: Causality-Guided Adversarial Multimodal Domain Generalization for Crisis Classification

Pingchuan Ma, Chengshuai Zhao, Bohan Jiang +5

Crisis classification in social media aims to extract actionable disaster-related information from multimodal posts, which is a crucial task for enhancing situational awareness and…

cs.LG2025

An Interventional Approach to Real-Time Disaster Assessment via Causal Attribution

Saketh Vishnubhatla, Alimohammad Beigi, Rui Heng Foo +5

Traditional disaster analysis and modelling tools for assessing the severity of a disaster are predictive in nature. Based on the past observational data, these tools prescribe how…

cs.LG2025

Assessing On-the-Ground Disaster Impact Using Online Data Sources

Saketh Vishnubhatla, Ujun Jeong, Bohan Jiang +4

Assessing the impact of a disaster in terms of asset losses and human casualties is essential for preparing effective response plans. Traditional methods include offline assessment…

cs.SI2025

Fediverse Sharing: Cross-Platform Interaction Dynamics between Threads and Mastodon Users

Ujun Jeong, Alimohammad Beigi, Anique Tahir +3

Traditional social media platforms, once envisioned as digital town squares, now face growing criticism over corporate control, content moderation, and privacy concerns. Events suc…

cs.SI2025

Navigating Decentralized Online Social Networks: An Overview of Technical and Societal Challenges in Architectural Choices

Ujun Jeong, Lynnette Hui Xian Ng, Kathleen M. Carley +1

Decentralized online social networks have evolved from experimental stages to operating at unprecedented scale, with broader adoption and more active use than ever before. Platform…