Rhetorical Device-Aware Sarcasm Detection with Counterfactual Data Augmentation
Abstract: Sarcasm is a complex form of sentiment expression, widely used in human daily life. Previous work primarily defines sarcasm as a form of verbal irony, which covers only a subset of real-world sarcastic expressions. However, sarcasm serves multifaceted functions and manifests through various rhetorical devices, such as echoic mentions, rhetorical questions, and hyperbole. To fully capture its complexity, this paper investigates fine-grained sarcasm classification through the lens of rhetorical devices, and introduces \textbf{RedSD}, a \textbf{R}h\textbf{E}torical \textbf{D}evice-Aware \textbf{S}arcasm \textbf{D}ataset with counterfactually augmented data.
To construct the dataset, we extract sarcastic dialogues from situation comedies (i.e., sitcoms), and summarize nine rhetorical devices commonly employed in sarcasm. We then propose a rhetorical device-aware counterfactual data generation pipeline facilitated by both Large Language Models (LLMs) and human revision. Additionally, we propose duplex counterfactual augmentation that generates counterfactuals for both sarcastic and non-sarcastic dialogues, to further enhance the scale and diversity of the dataset.
Experimental results on the dataset demonstrate that the fine-tuning models show more balanced performance over zero-shot models, including GPT-3.5 and LLaMA 3.1, underscoring the importance of integrating various rhetorical devices in sarcasm detection. Our dataset are avaliable at https://anonymous.4open.science/r/RedSD-742D.
Paper Type: Long
Research Area: Sentiment Analysis, Stylistic Analysis, and Argument Mining
Research Area Keywords: Sentiment Analysis, Sarcasm Detection
Contribution Types: Data resources, Data analysis
Languages Studied: English
Submission Number: 5512
Loading