Risk communication in times of disasters is complex, involving rapid and diverse communication in social networks (i.e., public and/or private agencies; residents) as well as limited mobilization capacity and operational constraints of physical infrastructure networks. Despite a growing literature on infrastructure interdependencies and co-dependent social-physical systems, an in-depth understanding of how risk communication in online social networks weighs into physical infrastructure networks during major disasters remains limited, let alone in compounding risk events. This study analyzes large-scale datasets of crisis mobility and activity-related social interactions and concerns available through social media (Twitter) for communities impacted by an ice storm in October 2020 in Oklahoma. Compounded by the COVID-19 pandemic, this aberrant ice storm caused significant traffic disruptions (among others) due to excessive ice accumulation. By using Twitter’s academic Application Programming Interface (API) that provides complete and unbiased data, geotagged tweets (~25.7K) were collected covering the entire state of Oklahoma. First, the study employes natural language processing techniques, such as topic modeling and Bidirectional Encoder Representations from Transformers (BERT) model to classify crisis narratives (e.g., tweets), and text quantification techniques to analyze them. Next, the geotagged quantified tweets are transformed into a weighting factor for the transportation infrastructure network by employing spatial analysis. Finally, using network analysis, this study develops an infrastructure risk map that integrates the co-located road network. The findings reveal that quantifying online social media content and communication patterns can highlight significant disruptions in critical infrastructure during compounding disaster events. By mapping the risks associated with road networks, the study provides emergency management agencies with valuable situational awareness, facilitating more efficient resource allocation and prioritization aimed at enhancing disaster response efforts.