IUST at ClimateActivism 2024: Towards Optimal Stance Detection: A Systematic Study of Architectural Choices and Data Cleaning Techniques

Ghazaleh Mahmoudi, Sauleh Eetemadi


Abstract
This work presents a systematic search of various model architecture configurations and data cleaning methods. The study evaluates the impact of data cleaning methods on the obtained results. Additionally, we demonstrate that a combination of CNN and Encoder-only models such as BERTweet outperforms FNNs. Moreover, by utilizing data augmentation, we are able to overcome the challenge of data imbalance.
Anthology ID:
2024.case-1.24
Volume:
Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024)
Month:
March
Year:
2024
Address:
St. Julians, Malta
Editors:
Ali Hürriyetoğlu, Hristo Tanev, Surendrabikram Thapa, Gökçe Uludoğan
Venues:
CASE | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
178–184
Language:
URL:
https://aclanthology.org/2024.case-1.24
DOI:
Bibkey:
Cite (ACL):
Ghazaleh Mahmoudi and Sauleh Eetemadi. 2024. IUST at ClimateActivism 2024: Towards Optimal Stance Detection: A Systematic Study of Architectural Choices and Data Cleaning Techniques. In Proceedings of the 7th Workshop on Challenges and Applications of Automated Extraction of Socio-political Events from Text (CASE 2024), pages 178–184, St. Julians, Malta. Association for Computational Linguistics.
Cite (Informal):
IUST at ClimateActivism 2024: Towards Optimal Stance Detection: A Systematic Study of Architectural Choices and Data Cleaning Techniques (Mahmoudi & Eetemadi, CASE-WS 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2024.case-1.24.pdf
Supplementary material:
 2024.case-1.24.SupplementaryMaterial.txt
Video:
 https://preview.aclanthology.org/ingest-2024-clasp/2024.case-1.24.mp4