Nick Obradovich

Rapid assessment of disaster damage using social media activity

Researchers show a correlation between per-capita social media activity and disaster damage, facilitating its rapid assessment. Could social media data aid in disaster response and damage assessment? Countries face both an increasing frequency and an increasing intensity of natural disasters resulting from climate change. During such events, citizens turn to social media platforms for disaster-related communication and information. Social media improves situational awareness, facilitates dissemination of emergency information, enables early warning systems, and helps coordinate relief efforts. In addition, the spatiotemporal distribution of disaster-related messages helps with the real-time monitoring and assessment of the disaster itself. We present a multiscale analysis of Twitter activity before, during, and after Hurricane Sandy. We examine the online response of 50 metropolitan areas of the United States and find a strong relationship between proximity to Sandy’s path and hurricane-related social media activity. We show that real and perceived threats, together with physical disaster effects, are directly observable through the intensity and composition of Twitter’s message stream. We demonstrate that per-capita Twitter activity strongly correlates with the per-capita economic damage inflicted by the hurricane. We verify our findings for a wide range of disasters and suggest that massive online social networks can be used for rapid assessment of damage caused by a large-scale disaster.

Big Data Sensors of Organic Advocacy: The Case of Leonardo DiCaprio and Climate Change

The strategies that experts have used to share information about social causes have historically been top-down, meaning the most influential messages are believed to come from planned events and campaigns. However, more people are independently engaging with social causes today than ever before, in part because online platforms allow them to instantaneously seek, create, and share information. In some cases this “organic advocacy” may rival or even eclipse top-down strategies. Big data analytics make it possible to rapidly detect public engagement with social causes by analyzing the same platforms from which organic advocacy spreads. To demonstrate this claim we evaluated how Leonardo DiCaprio’s 2016 Oscar acceptance speech citing climate change motivated global English language news (Bloomberg Terminal news archives), social media (Twitter postings) and information seeking (Google searches) about climate change. Despite an insignificant increase in traditional news coverage (54%; 95%CI: -144 to 247), tweets including the terms “climate change” or “global warming” reached record highs, increasing 636% (95%CI: 573–699) with more than 250,000 tweets the day DiCaprio spoke. In practical terms the “DiCaprio effect” surpassed the daily average effect of the 2015 Conference of the Parties (COP) and the Earth Day effect by a factor of 3.2 and 5.3, respectively. At the same time, Google searches for “climate change” or “global warming” increased 261% (95%CI, 186–335) and 210% (95%CI 149–272) the day DiCaprio spoke and remained higher for 4 more days, representing 104,190 and 216,490 searches. This increase was 3.8 and 4.3 times larger than the increases observed during COP’s daily average or on Earth Day. Searches were closely linked to content from Dicaprio’s speech (e.g., “hottest year”), as unmentioned content did not have search increases (e.g., “electric car”). Because these data are freely available in real time our analytical strategy provides substantial lead time for experts to detect and participate in organic advocacy while an issue is salient. Our study demonstrates new opportunities to detect and aid agents of change and advances our understanding of communication in the 21st century media landscape.

Nighttime temperature and human sleep loss in a changing climate

Analysis of reported sleep difficulties indicates that increases in nighttime temperatures reduce human sleep quality. Human sleep is highly regulated by temperature. Might climate change—through increases in nighttime heat—disrupt sleep in the future? We conduct the inaugural investigation of the relationship between climatic anomalies, reports of insufficient sleep, and projected climate change. Using data from 765,000 U.S. survey respondents from 2002 to 2011, coupled with nighttime temperature data, we show that increases in nighttime temperatures amplify self-reported nights of insufficient sleep. We observe the largest effects during the summer and among both lower-income and elderly respondents. We combine our historical estimates with climate model projections and detail the potential sleep impacts of future climatic changes. Our study represents the largest ever investigation of the relationship between sleep and ambient temperature and provides the first evidence that climate change may disrupt human sleep.

Climate change may speed democratic turnover

The electoral fate of incumbent politicians depends heavily upon voters’ well-being. Might climate change – by amplifying threats to human well-being – cause incumbent democratic politicians and parties to lose office more frequently? Here I conduct the first-ever investigation of the relationship between temperature, electoral returns, and future climate change. Using data from over 1.5 billion votes in over 4,800 electoral contests held in 19 countries between 1925 and 2011, coupled with meteorological data, I show that increases in annual temperatures above 21 °C (70 °F) markedly decrease officeholders’ vote share. I combine these empirical estimates with an ensemble of climate models to project the impact of climate change on the fate of future officeholders. Resulting forecasts indicate that by 2099 climate change may reduce average incumbent party vote share across all nations in the sample, with the most acute worsening occurring in poorer countries. If realized, these predictions indicate that climate change could amplify future rates of democratic turnover by causing incumbent parties and their politicians to lose office with increasing frequency.

Collective responsibility amplifies mitigation behaviors

How can individuals be convinced to act on climate change? It is widely assumed that emphasizing personal responsibility for climate change is effective at increasing pro-climate behavior whereas collectively framing the causes of climate change diffuses responsibility and dampens the incentive for individual action. We observe the opposite result. Here we find, across three experiments, that emphasizing collective responsibility for the causes of climate change increases pro-climate monetary donations by approximately 7 % in environmental group members and by 50 % in the general public. Further, highlighting collective responsibility amplifies intent to reduce future carbon emissions. In contrast, focusing on personal responsibility for climate change does not significantly alter donations to climate change advocacy or the intent for future pro-climate behavior. These effects replicate and persist multiple days after treatment.

Weather impacts expressed sentiment

We conduct the largest ever investigation into the relationship between meteorological conditions and the sentiment of human expressions. To do this, we employ over three and a half billion social media posts from tens of millions of individuals from both Facebook and Twitter between 2009 and 2016. We find that cold temperatures, hot temperatures, precipitation, narrower daily temperature ranges, humidity, and cloud cover are all associated with worsened expressions of sentiment, even when excluding weather-related posts. We compare the magnitude of our estimates with the effect sizes associated with notable historical events occurring within our data.

Detecting reciprocity at a global scale

Reciprocity is a widespread mechanism for cooperation in international relations. Reciprocity stabilizes cooperation from the level of microbes all the way up to humans interacting in small groups, but does reciprocity also underlie stable cooperation between larger human agglomerations, such as nation states? Famously, evolutionary models show that reciprocity could emerge as a widespread strategy for achieving international cooperation. However, existing studies have only detected reciprocity-driven cooperation in a small number of country pairs. We apply a new method for detecting mutual influence in dynamical systems to a new large-scale data set that records state interactions with high temporal resolution. Doing so, we detect reciprocity between many country pairs in the international system and find that these reciprocating country pairs exhibit qualitatively different cooperative dynamics when compared to nonreciprocating pairs. Consistent with evolutionary theories of cooperation, reciprocating country pairs exhibit higher levels of stable cooperation and are more likely to punish instances of noncooperation. However, countries in reciprocity-based relationships are also quicker to forgive single acts of noncooperation by eventually returning to previous levels of mutual cooperation. By contrast, nonreciprocating pairs are more likely to exploit each other’s cooperation via higher rates of defection. Together, these findings provide the strongest evidence to date that reciprocity is a widespread mechanism for achieving international cooperation.

TuringBox: An Experimental Platform for the Evaluation of AI Systems

We introduce TuringBox, a platform to democratize the study of AI. On one side of the platform, AI contributors upload existing and novel algorithms to be studied scientifically by others. On the other side, AI examiners develop and post machine intelligence tasks to evaluate and characterize the outputs of algorithms. We outline the architecture of such a platform, and describe two interactive case studies of algorithmic auditing on the platform.

Empirical evidence of mental health risks posed by climate change

Significance Wellbeing falters without sound mental health. Scholars have recently indicated that the impacts of climate change are likely to undermine mental health through a variety of direct and indirect mechanisms. Using daily meteorological data coupled with information from nearly 2 million randomly sampled US residents across a decade of data collection, we find that experience with hotter temperatures and added precipitation each worsen mental health, that multiyear warming associates with an increased prevalence of mental health issues, and that exposure to tropical cyclones, likely to increase in frequency and intensity in the future, is linked to worsened mental health. These results provide added large-scale evidence to the growing literature linking climate change and mental health. Sound mental health—a critical facet of human wellbeing—has the potential to be undermined by climate change. Few large-scale studies have empirically examined this hypothesis. Here, we show that short-term exposure to more extreme weather, multiyear warming, and tropical cyclone exposure each associate with worsened mental health. To do so, we couple meteorological and climatic data with reported mental health difficulties drawn from nearly 2 million randomly sampled US residents between 2002 and 2012. We find that shifting from monthly temperatures between 25 °C and 30 °C to >30 °C increases the probability of mental health difficulties by 0.5% points, that 1°C of 5-year warming associates with a 2% point increase in the prevalence of mental health issues, and that exposure to Hurricane Katrina associates with a 4% point increase in this metric. Our analyses provide added quantitative support for the conclusion that environmental stressors produced by climate change pose threats to human mental health.

Effects of environmental stressors on daily governance

Significance Public servants are often first responders to disasters, and the day-to-day completion of their jobs aids public health and safety. However, with respect to their individual psychological and physiological responses to environmental stressors, public sector workers may be harmed in much the same way as other citizens in society. We find that exposure to hotter temperatures reduces the activity of two groups of regulators—police officers and food safety inspectors—at times that the risks they are tasked with overseeing are highest. Given that we observe these effects in a country with high political institutionalization, our findings may have implications for the impacts of climate change on the functioning of regulatory governance in countries with lower political and economic development. Human workers ensure the functioning of governments around the world. The efficacy of human workers, in turn, is linked to the climatic conditions they face. Here we show that the same weather that amplifies human health hazards also reduces street-level government workers’ oversight of these hazards. To do so, we employ US data from over 70 million regulatory police stops between 2000 and 2017, from over 500,000 fatal vehicular crashes between 2001 and 2015, and from nearly 13 million food safety violations across over 4 million inspections between 2012 and 2016. We find that cold and hot temperatures increase fatal crash risk and incidence of food safety violations while also decreasing police stops and food safety inspections. Added precipitation increases fatal crash risk while also decreasing police stops. We examine downscaled general circulation model output to highlight the possible day-to-day governance impacts of climate change by 2050 and 2099. Future warming may augment regulatory oversight during cooler seasons. During hotter seasons, however, warming may diminish regulatory oversight while simultaneously amplifying the hazards government workers are tasked with overseeing.