| dc.description.abstract | The objective of this study is to examine and quantify the relationships among sociodemographic factors, damage claims and social media attention on areas in disasters. People seek situational awareness during disasters in order to perceive the risks and cope with community disruptions. With the increased use of social platforms, social media has become an important communication channel for people to share and seek situational information and support disaster response. Recent studies in disaster informatics have recognized the presence of bias in the representation of social media activity in different areas affected by disasters. To explore related factors for such bias, geo-tagged tweets have been used to study the extent of social media activity in disaster-affected areas to evaluate whether vulnerable populations remain silent on social media. However, less than 1% of all tweets are actually geo-tagged, therefore attempts to understand the representative of geotagged tweets to the general population have shown that certain populations are over or underrepresented. To overcome this limitation, incorporating relevant tweets identified based on their content is essential. Here, we conducted a content-based analysis to filter the tweets related to super-neighborhoods in Houston during Hurricane Harvey and cities in North Carolina during Hurricane Florence. By examining the relationships among sociodemographic factors, the number of damage claims and the volume of tweets, we find that social media attention concentrates in populous areas and is independent of education, language, unemployment, and median income. The relationship between population and social media attention is characterized by a sub-linear power law, indicating a large variation among the sparsely-populated areas. Using a machine learning model to label the topics of the tweets, we show that social media users pay more attention to rescue and donation related information, but the topic variation is consistent across areas with different levels of attention. These findings contribute to a better understanding of the spatial concentration of social media attention regarding posting and spreading situational information in disasters, and suggest planners and policymakers to better use social media data for equal disaster treatment. | |
