arXiv subjects

Ujun Jeong

Publications and source records attributed to Ujun Jeong.

11 recordsLinked to original sources

arXiv2026

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

During disasters, extracting causal relations from social media can strengthen situational awareness by identifying factors linked to casualties, physical damage, infrastructure disruption, and cascading impacts. However, disaster-related posts are often informal, fragmented, and context-dependent, and they may describe personal experiences rather than explicit causal relations. In this work, we examine whether Large Language Models (LLMs) can effectively extract causal relations from disaster-related social media posts. To this end, we (1) propose an expert-grounded evaluation framework that compares LLM-generated causal graphs with reference graphs derived from disaster-specific reports and (2) assess whether the extracted relations are supported by post-event evidence or instead reflect model priors. Our findings highlight both the potential and risks of using LLMs for causal relation extraction in disaster decision-support systems.

cs.CL↗

arXiv2025

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

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 facilitating timely emergency responses. However, the wide variation in crisis types makes achieving generalizable performance across unseen disasters a persistent challenge. Existing approaches primarily leverage deep learning to fuse textual and visual cues for crisis classification, achieving numerically plausible results under in-domain settings. However, they exhibit poor generalization across unseen crisis types because they 1. do not disentangle spurious and causal features, resulting in performance degradation under domain shift, and 2. fail to align heterogeneous modality representations within a shared space, which hinders the direct adaptation of established single-modality domain generalization (DG) techniques to the multimodal setting. To address these issues, we introduce a causality-guided multimodal domain generalization (MMDG) framework that combines adversarial disentanglement with unified representation learning for crisis classification. The adversarial objective encourages the model to disentangle and focus on domain-invariant causal features, leading to more generalizable classifications grounded in stable causal mechanisms. The unified representation aligns features from different modalities within a shared latent space, enabling single-modality DG strategies to be seamlessly extended to multimodal learning. Experiments on the different datasets demonstrate that our approach achieves the best performance in unseen disaster scenarios.

cs.LG↗

arXiv2025

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

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 assessments conducted on the ground, where volunteers and first responders work together to collect the estimate of losses through windshield surveys or on-ground inspection. However, these methods have a time delay and are prone to different biases. Recently, various online data sources, including social media, news reports, aerial imagery, and satellite data, have been utilized to evaluate the impact of disasters. Online data sources provide real-time data streams for estimating the offline impact. Limited research exists on how different online sources help estimate disaster impact at a given administrative unit. In our work, we curate a comprehensive dataset by collecting data from multiple online sources for a few billion-dollar disasters at the county level. We also analyze how online estimates compare with traditional offline-based impact estimates for the disaster. Our findings provide insight into how different sources can provide complementary information to assess the disaster.

cs.LG↗

arXiv2025

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

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 the current input state (e.g., environmental conditions, situation reports) results in a severity assessment. However, these systems are not meant to be interventional in the causal sense, where the user can modify the current input state to simulate counterfactual "what-if" scenarios. In this work, we provide an alternative interventional tool that complements traditional disaster modelling tools by leveraging real-time data sources like satellite imagery, news, and social media. Our tool also helps understand the causal attribution of different factors on the estimated severity, over any given region of interest. In addition, we provide actionable recourses that would enable easier mitigation planning. Our source code is publicly available.

cs.LG↗

arXiv2025

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

Decentralized online social networks have evolved from experimental stages to operating at unprecedented scale, with broader adoption and more active use than ever before. Platforms like Mastodon, Bluesky, Hive, and Nostr have seen notable growth, particularly following the wave of user migration after Twitter's acquisition in October 2022. As new platforms build upon earlier decentralization architectures and explore novel configurations, it becomes increasingly important to understand how these foundations shape both the direction and limitations of decentralization. Prior literature primarily focuses on specific architectures, resulting in fragmented views that overlook how different social networks encounter similar challenges and complement one another. This paper fills that gap by presenting a comprehensive view of the current decentralized online social network landscape. We examine four major architectures: federated, peer-to-peer, blockchain, and hybrid, tracing their evolution and evaluating how they support core social networking functions. By linking these architectural aspects to real-world cases, our work provides a foundation for understanding the societal implications of decentralized social platforms.

cs.SI↗

arXiv2025

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

Traditional social media platforms, once envisioned as digital town squares, now face growing criticism over corporate control, content moderation, and privacy concerns. Events such as Twitter's acquisition (now X) and major policy changes have pushed users toward alternative platforms like Mastodon and Threads. However, this diversification has led to user dispersion and fragmented discussions across the walled gardens of social media platforms. To address these issues, federation protocols like ActivityPub have been adopted, with Mastodon leading efforts to build decentralized yet interconnected networks. In March 2024, Threads joined this federation by introducing its Fediverse Sharing service, which enables interactions such as posts, replies, and likes between Threads and Mastodon users as if on a unified platform. Building on this development, we study the interactions between 20,000+ Threads users and 20,000+ Mastodon users over a ten-month period. Our work lays the foundation for research on cross-platform interactions and federation-driven platform integration.

cs.SI↗

arXiv2024

BlueTempNet: A Temporal Multi-network Dataset of Social Interactions in Bluesky Social

Decentralized social media platforms like Bluesky Social (Bluesky) have made it possible to publicly disclose some user behaviors with millisecond-level precision. Embracing Bluesky's principles of open-source and open-data, we present the first collection of the temporal dynamics of user-driven social interactions. BlueTempNet integrates multiple types of networks into a single multi-network, including user-to-user interactions (following and blocking users) and user-to-community interactions (creating and joining communities). Communities are user-formed groups in custom Feeds, where users subscribe to posts aligned with their interests. Following Bluesky's public data policy, we collect existing Bluesky Feeds, including the users who liked and generated these Feeds, and provide tools to gather users' social interactions within a date range. This data-collection strategy captures past user behaviors and supports the future data collection of user behavior.

cs.SI↗

arXiv2023

User Migration across Multiple Social Media Platforms

After Twitter's ownership change and policy shifts, many users reconsidered their go-to social media outlets and platforms like Mastodon, Bluesky, and Threads became attractive alternatives in the battle for users. Based on the data from over 14,000 users who migrated to these platforms within the first eight weeks after the launch of Threads, our study examines: (1) distinguishing attributes of Twitter users who migrated, compared to non-migrants; (2) temporal migration patterns and associated challenges for sustainable migration faced by each platform; and (3) how these new platforms are perceived in relation to Twitter. Our research proceeds in three stages. First, we examine migration from a broad perspective, not just one-to-one migration. Second, we leverage behavioral analysis to pinpoint the distinct migration pattern of each platform. Last, we employ a Large Language Model (LLM) to discern stances towards each platform and correlate them with the platform usage. This in-depth analysis illuminates migration patterns amid competition across social media platforms.

cs.SI↗

arXiv2023

Exploring Platform Migration Patterns between Twitter and Mastodon: A User Behavior Study

A recent surge of users migrating from Twitter to alternative platforms, such as Mastodon, raised questions regarding what migration patterns are, how different platforms impact user behaviors, and how migrated users settle in the migration process. In this study, we elaborate on how we investigate these questions by collecting data over 10,000 users who migrated from Twitter to Mastodon within the first ten weeks following the ownership change of Twitter. Our research is structured in three primary steps. First, we develop algorithms to extract and analyze migration patterns. Second, by leveraging behavioral analysis, we examine the distinct architectures of Twitter and Mastodon to learn how user behaviors correspond with the characteristics of each platform. Last, we determine how particular behavioral factors influence users to stay on Mastodon. We share our findings of user migration, insights, and lessons learned from the user behavior study.

cs.SI↗

arXiv2022

Nothing Stands Alone: Relational Fake News Detection with Hypergraph Neural Networks

Nowadays, fake news easily propagates through online social networks and becomes a grand threat to individuals and society. Assessing the authenticity of news is challenging due to its elaborately fabricated contents, making it difficult to obtain large-scale annotations for fake news data. Due to such data scarcity issues, detecting fake news tends to fail and overfit in the supervised setting. Recently, graph neural networks (GNNs) have been adopted to leverage the richer relational information among both labeled and unlabeled instances. Despite their promising results, they are inherently focused on pairwise relations between news, which can limit the expressive power for capturing fake news that spreads in a group-level. For example, detecting fake news can be more effective when we better understand relations between news pieces shared among susceptible users. To address those issues, we propose to leverage a hypergraph to represent group-wise interaction among news, while focusing on important news relations with its dual-level attention mechanism. Experiments based on two benchmark datasets show that our approach yields remarkable performance and maintains the high performance even with a small subset of labeled news data.

cs.SI↗

arXiv2021

FBAdtTracker: An Interactive Data Collection and Analysis Tool for Facebook Advertisements

The growing use of social media has led to drastic changes in our decision-making. Especially, Facebook offers marketing API which promotes business to target potential groups who are likely to consume their items. However, this service can be abused by malicious advertisers who attempt to deceive people by disinformation such as propaganda and divisive opinion. To counter this problem, we introduce a new application named FBAdTracker. The purpose of this application is to provide an integrated data collection and analysis system for current research on fact-checking related to Facebook advertisements. Our system is capable of monitoring up-to-date Facebook ads and analyzing ads retrieved from Facebook Ads Library.

cs.IR↗