Dynamic Characteristics and Evolution Analysis of Information Dissemination Theme of Social Networks under Emergencies

Abstract

Social media has become an essential channel for the public to create and obtain information during emergencies. As the theme of public concern for emergencies changes over time, there is a lack of research on its dynamic evolution from its latent stage. This paper selects the Henan rainstorm event as a case study and extracts the theme characteristics by combining the life cycle theory and Latent Dirichlet Allocation (LDA) model. It integrates the Term Frequency–Inverse Document Frequency (TF-IDF) and Pointwise Mutual Information (PMI) algorithms as the theme-coding data source to build a dynamic theme propagation model for emergencies. Our research results showed that the theme coding effectively verified the assumption of latent development trends. The dynamic theme model could reveal the theme characteristics of different time series stages of emergencies, analyze the law of the theme evolution of the network’s public opinion, and provide practical and theoretical insights for the emergency management of urban cities.

Exhaustive Insights Towards Social-Media Driven Disaster Management Approaches

“… This type of method mainly emphasizes channeling the identified events of disaster to an appropriate communication channel to forward the information to emergency services. Some of the existing research frameworks towards information dissemination implemented are as follows Mobile computing-based emergency management (Astarita et al [37]), Geospatial-information based disaster management (Ghawana et al [38]), User behavior centric framework for disaster screening (Han & Wang [39]), Hubframework connecting the critical community with local emergency management team (Mitcham et al [40]), Micro-Macro level-based disaster alters using social network (Samaddar et al [41]), Edge computing-based named data network for disaster response system (Tran & Kim [42]), Acquisition framework for disaster location analysis (Yang et al [43]), Multimodal framework for disaster data evaluation (Zhang et al [44]), Model for Dynamic theme propagation for rainstorm detection (Zhang et al [45]), Integrated machine learning and spatiotemporal analytical framework (Zhang et al [46]). A closer look into these study models shows that they are mainly meant for the authorities to use social media to propagate safety guidelines, evacuation routes, and emergency information to the affected population.…”

“…Several dominant research-based approaches are used to analyze natural disasters viz. i) Interdisciplinary Research (Tavra et al [65], Khattar & Quadri [60], Ide & Nomura [58]), ii) Risk-Based Approaches ((Psaroudakis et al [30]), iii) Datadriven Analysis (Ghawana et al [38], Vavassori et al [52], Zhang et al [45]), iv) Resilience Frameworks (Maxant et al [51], Divjak and Lapaine [47], Du et al [49]). Under interdisciplinary research scheme, it is considered that natural disasters are complex events involving multiple factors, including physical, social, economic, and environmental dimensions.…”

“…Social media platforms have become increasingly important tools for natural disaster management, with several prominent attributes that have the potential to influence disaster response efforts viz. i) Real-Time Information Sharing (Aramendia et al [26], Beltramone & Gomes [27], Cheong et al [28], Karmegam et al [59], Turay and S. Gbetuwa [68], Zhu et al [66]), ii) Crowdsourced Data Collection (Tavra et al [65], Astarita et al [37]), iii) Two-Way Communication (Tran & Kim [42], Zhang et al [45]), iv) Public Engagement and Mobilization (Malla et al [70], Tarchiani et al [35], Al-Mueed et al [29], Mitcham et al [40]), v) Information Aggregation and Analysis (Malla et al [70], Han & Wang [39], Tavra et al [65]), vi) Crisis Mapping and Visualization (Divjak and Lapaine [47], Du et al [49], Durrant et al [50], Maxant et al [51], Vavassori et al [52]). Under attributes of real-time information sharing, it is believed that social media allows for the rapid dissemination of information during disasters, enabling authorities, organizations, and individuals to share updates on hazards, evacuation orders, shelter locations, road closures, and other important developments in real time.…”

The impact of Public Health Emergency (PHE) on the news dissemination strength: Evidence from Chinese-Speaking Vloggers on YouTube

“…First, time factors are considered as important factors affecting the news dissemination during public health emergencies [ 21 ]. In different life cycles, there are great differences in the propagation speed and diffusion volumes of event-related information on social media [ 22 , 23 ]. Second, media factors are also significant factors influencing the news dissemination during public health emergencies.…”