The Role of Conversation Context for Sarcasm Detection in Online Interactions

TL;DR

This paper explores how incorporating conversation context improves sarcasm detection in social media, demonstrating that context-aware LSTM models outperform response-only models and analyzing what contextual cues trigger sarcasm.

Contribution

It introduces and evaluates context-aware LSTM models with attention mechanisms for sarcasm detection, highlighting the importance of conversation context and providing insights into contextual triggers.

Findings

Context-aware LSTM models outperform response-only models.

Attention mechanisms help identify sarcastic cues in context.

Qualitative analysis aligns with human judgments.

Abstract

Computational models for sarcasm detection have often relied on the content of utterances in isolation. However, speaker's sarcastic intent is not always obvious without additional context. Focusing on social media discussions, we investigate two issues: (1) does modeling of conversation context help in sarcasm detection and (2) can we understand what part of conversation context triggered the sarcastic reply. To address the first issue, we investigate several types of Long Short-Term Memory (LSTM) networks that can model both the conversation context and the sarcastic response. We show that the conditional LSTM network (Rocktaschel et al., 2015) and LSTM networks with sentence level attention on context and response outperform the LSTM model that reads only the response. To address the second issue, we present a qualitative analysis of attention weights produced by the LSTM models with attention and discuss the results compared with human performance on the task.