Exploring Data Augmentation for Classification of Climate Change Denial: Preliminary Study
In order to address the growing need of monitoring climate-change denial narratives in online sources, NLP-based methods have been acknowledged to have an potential to automate this process. In this paper we report on preliminary experiments of exploiting Data Augmentation techniques for improving climate change denial classification, focusing on a selection of known and some not reported elsewhere augmentation transformations that replace certain type of named entities, and which guarantee high probability of preserving labels. We also elaborate on the creation of a new benchmark dataset consisting of text snippets extracted from online news labeled with fine-grained climate change denial type.
PISKORSKI Jakub;
NIKOLAIDIS Nikolaos;
STEFANOVITCH Nicolas;
KOTSEVA Bonka;
VIANINI Irene;
KHARAZI Sopho;
LINGE Jens;
2023-09-25
Elsevier
JRC128613
1613-0073 (online),
https://ceur-ws.org/Vol-3117/paper11.pdf,
https://publications.jrc.ec.europa.eu/repository/handle/JRC128613,
Additional supporting files
| File name | Description | File type | |
|---|
