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

Download PDF
Open Webpage

Ghazaleh Mahmoudi, Sauleh Eetemadi

Published: 01 Jan 2024, Last Modified: 19 Jun 2024CASE 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
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.