Anjum, U., Zadorozhny, V., & Krishnamurthy, P. (2023). Localization of Events Using Neural Networks in Twitter Data. In Jaziar Radianti, Ioannis Dokas, Nicolas Lalone, & Deepak Khazanchi (Eds.), Proceedings of the 20th International ISCRAM Conference (pp. 909–919). Omaha, USA: University of Nebraska at Omaha.
Abstract: In this paper, we develop a model with neural networks to localize events using microblogging data. Localization is the task of finding the location of an event and can be done by discovering event signatures in microblogging data. We use the deep learning methodology of Bi-directional Long Short-Term Memory (Bi-LSTM) to learn event signatures. We propose a methodology for labeling the Twitter date for use in Bi-LSTM However, there might not be enough data available to train the Bi-LSTM and learn the event signatures. Hence, the data is augmented using generative adversarial networks (GAN). Finally, we combine event signatures at different temporal and spatial granularity to improve the accuracy of event localization. We use microblogging data collected from Twitter to evaluate our model and compare it with other baseline methods.
|
|
Rocco Sergio Palermo, & Antonio De Nicola. (2022). A Simulation Framework for Epidemic Spreading in Semantic Social Networks. In Rob Grace, & Hossein Baharmand (Eds.), ISCRAM 2022 Conference Proceedings – 19th International Conference on Information Systems for Crisis Response and Management (pp. 266–273). Tarbes, France.
Abstract: Epidemic spreading simulation in social networks denotes a set of techniques that allow to assess the temporal evolution and the consequences of a pandemic. They were largely used by governments and International health organizations during the COVID-19 world crisis to decide the appropriate countermeasures to limit the diffusion of the disease. Among them, the existing simulation techniques based on a network model aimed at studying the infectious disease dynamics have a prominent role and are widely adopted. However, even if they leverage the topological structure of a social network, they disregard the intrinsic and individual features of its members. A semantic social network is defined as a structure consisting of interlinking layers, which include a social network layer, to represent people and their relationships and a concept network layer, to represent concepts, their ontological relationships and implicit similarities. Here, we propose a novel epidemic simulation framework that allows to describe a community of people as a semantic social network, to adopt the most commonly used compartmental models for describing epidemic spreading, such as Susceptible-Infected-Susceptible (SIS) or Susceptible-Infected-Removed (SIR), and to enable semantic reasoning to increase the accuracy of the simulation. Finally, we show how to use the framework to simulate the impact of a pandemic in a community where the job of each member is known in advance.
|
|
Yan Wang, Qi Wang, & John Taylor. (2021). Loss of Resilience in Human Mobility across Severe Tropical Cyclones of Different Magnitudes. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 755–765). Blacksburg, VA (USA): Virginia Tech.
Abstract: Severe tropical cyclones impose threats on highly populated coastal urban areas, thereby, understanding and predicting human movements plays a critical role in evaluating disaster resilience of human society. However, limited research has focused on tropical cyclones and their influence on human mobility resilience. This preliminary study examined the strength and duration of human mobility perturbation across five significant tropical storms and their affected eight urban areas using Twitter data. The results suggest that tropical cyclones can significantly perturb human movements by changing travel frequencies and displacement probability distributions. While the power-law still best described the pattern of human movements, the changes in the radii of gyration were significant and resulted in perturbation and loss of resilience in human mobility. The findings deepen the understanding about human-environment interactions under extreme events, improve our ability to predict human movements using social media data, and help policymakers improve disaster evacuation and response.
|
|
Nathan Elrod, Pranav Mahajan, Monica Katragadda, Shane Halse, & Jess Kropczynski. (2021). An Exploration of Methods Using Social Media to Examine Local Attitudes Towards Mask-Wearing During a Pandemic. In Anouck Adrot, Rob Grace, Kathleen Moore, & Christopher W. Zobel (Eds.), ISCRAM 2021 Conference Proceedings – 18th International Conference on Information Systems for Crisis Response and Management (pp. 345–358). Blacksburg, VA (USA): Virginia Tech.
Abstract: During the COVID-19 health crisis, local public offcials expend considerable energy encouraging citizens to comply with prevention measures in order to reduce the spread of infection. During the pandemic, mask-wearing has been accepted among health offcials as a simple preventative measure; however, some local areas have been more likely to comply than others. This paper explores methods to better understand local attitudes towards mask-wearing as a tool for public health offcials' situational awareness when preparing public messaging campaigns. This exploration compares three methods to explore local attitudes: sentiment analysis, n-grams, and hashtags. We also explore hashtag co-occurrence networks as a starting point to begin the filtering process. The results show that while sentiment analysis is quick and easy to employ, the results oer little insight into specific local attitudes towards mask-wearing, while examining hashtags and hashtag co-occurrence networks may be used a tool for a more robust understanding of local areas when attempting to gain situational awareness.
|
|
Haiyan Hao, & Yan Wang. (2020). Hurricane Damage Assessment with Multi-, Crowd-Sourced Image Data: A Case Study of Hurricane Irma in the City of Miami. In Amanda Hughes, Fiona McNeill, & Christopher W. Zobel (Eds.), ISCRAM 2020 Conference Proceedings – 17th International Conference on Information Systems for Crisis Response and Management (pp. 825–837). Blacksburg, VA (USA): Virginia Tech.
Abstract: The massive crowdsourced data generated on social networking platforms (e.g. Twitter and Flickr) provide free, real-time data for damage assessment (DA) even during catastrophes. Recent studies leveraging crowdsourced data for DA mainly focused on analyzing textual formats. Crowdsourced images can provide rich and objective information about damage conditions, however, are rarely researched for DA purposes. The highly-varied content and loosely-defined damage forms make it difficult to process and analyze the crowdsourced images. To address this problem, we propose a data-driven DA method based on multi-, crowd-sourced images, which includes five machine learning classifiers organized in a hierarchical structure. The method is validated with a case study investigating the damage condition of the City of Miami caused by Hurricane Irma. The outcome is then compared with a metric derived from NFIP insurance claims data. The proposed method offers a resource for rapid DA that supplements conventional DA methods.
|
|