Cross-Lingual and Cross-Domain Crisis Classification for Low-Resource Scenarios
Preprint
Abstract
Social media data has emerged as a useful source of timely information about real-world crisis events. One of the main tasks related to the use of social media for disaster management is the automatic identification of crisis-related messages. Most of the studies on this topic have focused on the analysis of data for a particular type of event in a specific language. This limits the possibility of generalizing existing approaches because models cannot be directly applied to new types of events or other languages. In this work, we study the task of automatically classifying messages that are related to crisis events by leveraging cross-language and cross-domain labeled data. Our goal is to make use of labeled data from high-resource languages to classify messages from other (low-resource) languages and/or of new (previously unseen) types of crisis situations. For our study we consolidated from the literature a large unified dataset containing multiple crisis events and languages. Our empirical findings show that it is indeed possible to leverage data from crisis events in English to classify the same type of event in other languages, such as Spanish and Italian (80.0% F1-score). Furthermore, we achieve good performance for the cross-domain task (80.0% F1-score) in a cross-lingual setting. Overall, our work contributes to improving the data scarcity problem that is so important for multilingual crisis classification. In particular, mitigating cold-start situations in emergency events, when time is of essence.Keywords
All Related Versions
This publication has 7 references indexed in Scilit:
- Hate speech detection is not as easy as you may think: A closer look at model validation (extended version)Information Systems, 2022
- Domain Adaptation with Reconstruction for Disaster Tweet Classification2020
- Exploitation of Social Media for Emergency Relief and Preparedness: Recent Research and TrendsInformation Systems Frontiers, 2018
- Robust Detection of Extreme Events Using Twitter: Worldwide Earthquake MonitoringIEEE Transactions on Multimedia, 2018
- A New Mashup Based Method for Event Detection from Social MediaInformation Systems Frontiers, 2018
- Crisis informatics—New data for extraordinary timesScience, 2016
- A Survey on Transfer LearningIEEE Transactions on Knowledge and Data Engineering, 2009