Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

7-2023

Abstract

Twitter has become an alternative information source during a crisis. However, the short, noisy nature of tweets hinders information extraction. While models trained with standard Twitter crisis datasets accomplished decent performance, it remained a challenge to generalize to unseen crisis events. Thus, we proposed adding “difficult” negative examples during training to improve model generalization for Twitter crisis detection. Although adding random noise is a common practice, the impact of difficult negatives, i.e., negative data semantically similar to true examples, was never examined in NLP. Most of existing research focuses on the classification task, without considering the primary information need of crisis responders. In our study, we implemented multiple sequence tagging models and studied quantitatively and qualitatively the impact of difficult negatives on sequence tagging. We evaluated models on unseen events and showed that difficult negative forced models to generalize better, leading to more accurate information extraction in a real-world application.

Keywords

Twitter, Crisis Detection, Difficult Negative Data, Negative Mining

Discipline

Databases and Information Systems | Social Media

Research Areas

Data Science and Engineering

Publication

Proceedings of Pacific Asia Conference on Information Systems 2023, Nanchang, China, July 8-12

First Page

1

Last Page

15

City or Country

Nanchang, China

Copyright Owner and License

Authors

Additional URL

https://aisel.aisnet.org/pacis2023/156

Share

COinS