Investigating Chain-of-thought with ChatGPT for Stance Detection on Social Media
It addresses stance detection for social media analysis, but appears incremental as it applies an existing method to a new domain.
This paper tackled stance detection on social media by applying the Chain-of-Thought approach with ChatGPT, showing it achieves superior accuracy compared to traditional methods.
Stance detection predicts attitudes towards targets in texts and has gained attention with the rise of social media. Traditional approaches include conventional machine learning, early deep neural networks, and pre-trained fine-tuning models. However, with the evolution of very large pre-trained language models (VLPLMs) like ChatGPT (GPT-3.5), traditional methods face deployment challenges. The parameter-free Chain-of-Thought (CoT) approach, not requiring backpropagation training, has emerged as a promising alternative. This paper examines CoT's effectiveness in stance detection tasks, demonstrating its superior accuracy and discussing associated challenges.