Multilingual Serviceability Model for Detecting and Ranking Help Requests on Social Media during Disasters

Abstract

Social media users expect quick and high-quality responses from emergency services when seeking help. However, these organizations face difficulties in detecting and prioritizing critical requests due to the overwhelming amount of information on social media and their limited human resources to tackle it during mass emergencies or disaster events. The situation is exacerbated when users communicate in different or native languages, which can be expected during disasters. While recent studies have focused on characterizing and automatically detecting help requests on social media, they focused on non-behavioral features and monolingual data, primarily in English. Thus, a key gap exists in analyzing multilingual requests on social media for public services. In this paper, we introduce a knowledge distillation framework called MulTMR (Multiple Teachers Model for detecting and Ranking), which combines the power of both task-related and behavior-guided models as diverse teachers for training a student model to efficiently detect serviceable request messages across languages and regions on social media during natural disaster events. We demonstrate that the presented framework can enhance performance (with an AUC improvement of up to 10%) in various scenarios of multilingual test data. Our results, which were validated on real-world data collected in three languages during ten disasters across seven countries, indicate the use of behavior-guided teacher models in MulTMR can increase attention to relevant indicators of serviceability characteristics. The application of the MulTMR framework through a streaming data analytics tool could reduce the cognitive load on personnel within social media teams of emergency services. Further, its application could inform how to leverage human behavior characteristics in creating automated models for social media analytics to design systems in other public service domains beyond emergency management.