AI–Social Media Integration for Crisis Management: A Systematic Review of Data and Learning Aspects

Abstract

As natural disasters and crises increase globally in both frequency and severity, researchers have been exploring innovative technological solutions to manage them effectively. This systematic review examines the integration of artificial intelligence (AI) with social media platforms for crisis management, identifying and categorizing key components of AI-driven systems into data and learning aspects. It introduces a dual-aspect analytical taxonomy that provides a structured framework for analyzing how data and learning dimensions interact in AI-driven crisis management solutions. Following the PRISMA methodology, the review analyzed 30 high-impact, peer-reviewed journal articles published in English between 2020 and 2024 across major academic databases. The quality of the studies was assessed based on journal ranking and methodological rigor to ensure reliability and minimize bias. The analysis revealed several interconnected trends: text remains the dominant data modality (60%), while multimodal analysis (33%) and image-based analysis (7%) are gaining traction. Throughout these studies, deep learning models consistently demonstrated superior performance compared to traditional machine learning approaches, with hybrid methodologies significantly enhancing overall model efficiency. Notably, the majority of research (73%) concentrated on during-disaster phases, highlighting the critical need for real-time intervention solutions. Twitter/X emerged as the overwhelming primary data source (73%), creating potential platform dependency issues. Despite considerable advancements, the field continues to face persistent challenges, including an over-reliance on single platforms, insufficient real-time AI models, and complexities in multimodal data fusion. To advance crisis management capabilities, future research directions should address cross-domain generalizability, enhance real-time processing capabilities, and develop improved fusion techniques that can ultimately lead to more effective and timely disaster response systems.