Social Media Attributions in the Context of Water Crisis
This addresses the need for scalable, AI-driven methods to complement traditional surveys in political science for analyzing public attributions of collective misfortunes, though it is incremental as it applies existing neural techniques to a new domain.
The paper tackled the problem of automatically extracting attribution factors for natural disasters from social media data, focusing on the Chennai water crisis, and achieved 81.34% accuracy on attribution detection and 71.19% on attribution resolution using a neural classifier.
Attribution of natural disasters/collective misfortune is a widely-studied political science problem. However, such studies are typically survey-centric or rely on a handful of experts to weigh in on the matter. In this paper, we explore how can we use social media data and an AI-driven approach to complement traditional surveys and automatically extract attribution factors. We focus on the most-recent Chennai water crisis which started off as a regional issue but rapidly escalated into a discussion topic with global importance following alarming water-crisis statistics. Specifically, we present a novel prediction task of attribution tie detection which identifies the factors held responsible for the crisis (e.g., poor city planning, exploding population etc.). On a challenging data set constructed from YouTube comments (72,098 comments posted by 43,859 users on 623 relevant videos to the crisis), we present a neural classifier to extract attribution ties that achieved a reasonable performance (Accuracy: 81.34\% on attribution detection and 71.19\% on attribution resolution).