Knowledge-embedded Prompt Learning for Zero-shot Social Media Text Classification

Abstract

Social media plays an irreplaceable role in shaping the way information is created shared and consumed. While it provides access to a vast amount of data, extracting and analyzing useful insights from complex and dynamic social media data can be challenging. Deep learning models have shown promise in social media analysis tasks, but such models require a massive amount of labelled data which is usually unavailable in real-world settings. Additionally, these models lack common-sense knowledge which can limit their ability to generate comprehensive results. To address these challenges, we propose a knowledge-embedded prompt learning model for zero-shot social media text classification. Our experimental results on four social media datasets demonstrate that our proposed approach outperforms other well-known baselines.