During the last few decades, scientific capabilities for understanding and predicting weather and climate risks have advanced rapidly. At the same time, technological advances, such as the Internet, mobile devices, and social media, are transforming how people exchange and interact with information. In this modern information environment, risk communication, interpretation, and decision-making are rapidly evolving processes that intersect across space, time, and society. Instead of a linear or iterative process in which individual members of the public assess and respond to distinct pieces of weather forecast or warning information, this article conceives of weather prediction, communication, and decision-making as an interconnected dynamic system. In this expanded framework, information and uncertainty evolve in conjunction with people’s risk perceptions, vulnerabilities, and decisions as a hazardous weather threat approaches; these processes are intertwined with evolving social interactions in the physical and digital worlds. Along with the framework, the article presents two interdisciplinary research approaches for advancing the understanding of this complex system and the processes within it: analysis of social media streams and computational natural–human system modeling. Examples from ongoing research are used to demonstrate these approaches and illustrate the types of new insights they can reveal. This expanded perspective together with research approaches, such as those introduced, can help researchers and practitioners understand and improve the creation and communication of information in atmospheric science and other fields.

This paper presents a system for classifying disaster-related tweets. The focus is on Twitter data generated before, during, and after Hurricane Sandy, which impacted New York in the fall of 2012. We propose an annotation schema for identifying relevant tweets as well as the more fine-grained categories they represent, and develop feature-rich classifiers for relevance and fine-grained categorization.

This article investigates the dynamic ways that people communicate, assess, and respond as a weather threat evolves. It uses social media data, which offer unique records of what people convey about their real-world risk contexts. Twitter narratives from 53 people who were in a mandatory evacuation zone in a New York City neighborhood during Hurricane Sandy in 2012 were qualitatively analyzed. The study provides rich insight into the complex, dynamic information behaviors and risk assessments of people at risk, and it illustrates how social media data can be collected, sampled, and analyzed to help provide this understanding. Results show that this sample of people at significant risk attended to forecast information and evacuation orders as well as multiple types of social and environmental cues. Although many tweeted explicitly about the mandatory evacuation order, forecast information was usually referenced only implicitly. Social and environmental cues grew more important as the threat approached and often triggered heightened risk perceptions or protective actions. The results also reveal the importance of different aspects of people’s cognitive and affective risk perceptions as well as specific emotions (e.g., fear, anger) for understanding risk assessments. People discussed a variety of preparatory and protective behavioral responses and exhibited multiple types of coping responses (e.g., humor) as the threat evolved. People’s risk assessments and responses were closely intertwined, and their risk perceptions were not continuously elevated as the hurricane approached; they exhibited different ways of interpreting, coping, and responding as they accessed and processed evolving information about the threat.

A large amount of social media data is generated during natural disasters, and identifying the relevant portions of this data is critical for researchers attempting to understand human behavior, the effects of information sources, and preparatory actions undertaken during these events. In order to classify human behavior during hazard events, we employ machine learning for two tasks: identifying hurricane related tweets and classifying user evacuation behavior during hurricanes. We show that feature-based and deep learning methods provide different benefits for tweet classification, and ensemble-based methods using linguistic, temporal, and geospatial features can effectively classify user behavior.

In the field of metaphor detection, deep learning systems are the ubiquitous and achieve strong performance on many tasks. However, due to the complicated procedures for manually identifying metaphors, the datasets available are relatively small and fraught with complications. We show that using syntactic features and lexical resources can automatically provide additional high-quality training data for metaphoric language, and this data can cover gaps and inconsistencies in metaphor annotation, improving state-of-the-art word-level metaphor identification. This novel application of automatically improving training data improves classification across numerous tasks, and reconfirms the necessity of high-quality data for deep learning frameworks.