Ranking and grouping social media requests for emergency services using serviceability model

Abstract

Social media has become an alternative communication mechanism for the public to reach out to emergency services during time-sensitive events. However, the information overload of social media experienced by these services, coupled with their limited human resources, challenges them to timely identify, prioritize, and organize critical requests for help. In this paper, we first present a formal model of serviceability called Social-EOC, which describes the elements of a serviceable message posted in social media expressing a request. Using the serviceability model, we then describe a system for the discovery and ranking of highly serviceable requests as well as for re-ranking requests by semantic grouping to reduce redundancy and facilitate the browsing of requests by responders. We validate the model for emergency services by experimenting with six crisis event datasets and ground truth provided by emergency professionals. Our experiments demonstrate that features based on both serviceability model and social connectedness improve the performance of discovering and ranking (nDCG gain up to 25%) service requests over different baselines. We also empirically validate the existence of redundancy and semantic coherence among the serviceable requests using our semantic grouping approach, which shows the significance and need for grouping similar requests to save the time of emergency services. Thus, an application of serviceability model could reduce cognitive load on emergency servicers in filtering, ranking, and organizing public requests on social media at scale.

Improving Crisis Events Detection Using DistilBERT with Hunger Games Search Algorithm

“…Every one of these studies, even so, starts concentrating on disaster-related Twitter posts rather than sub-categories of tweets such as the destruction of infrastructure, human destruction, source of information need, and availability. Little research has concentrated on classifying tweets throughout a crisis [28,29]. Madichetty and Sridevi [30] concentrated on a design to detect the accessibility and scarcity of resources.…”

Utilizing microblogs for optimized real-time resource allocation in post-disaster scenarios

“…In another recent study, (Purohit et al. 2020 ) developed a serviceability model and a system to identify and rank highly serviceable requests during a disaster. The system also possesses a facility to re-rank service requests by semantic grouping to reduce redundancy and to assist the browsing of requests.…”

On detecting urgency in short crisis messages using minimal supervision and transfer learning

“…We only cite a few recent papers by way of reference. Recently, (Purohit et al 2020) have described a method to rank and group social media requests for emergency services, a work that is particularly relevant since the outbreak of COVID-19. Recent work in opinion mining (e.g., see Keyvanpour et al 2020), especially using lexicons and machine learning in social media, is also relevant to our work.…”