Comparing News Framing of Migration Crises using Zero-Shot Classification

Nikola Ivačič, Matthew Purver, Fabienne Lind, Senja Pollak, Hajo Boomgaarden, Veronika Bajt


Abstract
We present an experiment on classifying news frames in a language unseen by the learner, using zero-shot cross-lingual transfer learning. We used two pre-trained multilingual Transformer Encoder neural network models and tested with four specific news frames, investigating two approaches to the resulting multi-label task: Binary Relevance (treating each frame independently) and Label Power-set (predicting each possible combination of frames). We train our classifiers on an available annotated multilingual migration news dataset and test on an unseen Slovene language migration news corpus, first evaluating performance and then using the classifiers to analyse how media framed the news during the periods of Syria and Ukraine conflict-related migrations.
Anthology ID:
2024.rfp-1.3
Volume:
Proceedings of the First Workshop on Reference, Framing, and Perspective @ LREC-COLING 2024
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Pia Sommerauer, Tommaso Caselli, Malvina Nissim, Levi Remijnse, Piek Vossen
Venues:
rfp | WS
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
18–27
Language:
URL:
https://aclanthology.org/2024.rfp-1.3
DOI:
Bibkey:
Cite (ACL):
Nikola Ivačič, Matthew Purver, Fabienne Lind, Senja Pollak, Hajo Boomgaarden, and Veronika Bajt. 2024. Comparing News Framing of Migration Crises using Zero-Shot Classification. In Proceedings of the First Workshop on Reference, Framing, and Perspective @ LREC-COLING 2024, pages 18–27, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Comparing News Framing of Migration Crises using Zero-Shot Classification (Ivačič et al., rfp-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.rfp-1.3.pdf