Why Do We Laugh? Annotation and Taxonomy Generation for Laughable Contexts in Spontaneous Text Conversation

2025-01-28

AI Summary

This study addresses the coarse-grained and uninterpretable nature of laughter detection in conversational AI. We introduce the first annotated dataset for humor propensity in spontaneous Japanese textual dialogues and propose a fine-grained, interpretable taxonomy of ten laughter-inducing mechanisms (e.g., empathic affiliation, humorous surprise). Methodologically, we combine multi-annotator consensus labeling with GPT-4–assisted explanation generation, followed by human-led clustering to derive the taxonomy—thereby moving beyond conventional binary laughter detection. To our knowledge, this is the first attribution framework specifically designed for spontaneous dialogue. Experimental results show that GPT-4 achieves 43.14% F1 on humor identification, demonstrating both the practical utility of our taxonomy for enhancing model performance and its potential for cross-task transfer.

Technology Category

• Natural Language Processing: Conversational AI/Dialog Systems
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Philosophy and Ethics of AI: Accountability, Interpretability & Explainability

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Laughter serves as a multifaceted communicative signal in human interaction, yet its identification within dialogue presents a significant challenge for conversational AI systems. This study addresses this challenge by annotating laughable contexts in Japanese spontaneous text conversation data and developing a taxonomy to classify the underlying reasons for such contexts. Initially, multiple annotators manually labeled laughable contexts using a binary decision (laughable or non-laughable). Subsequently, an LLM was used to generate explanations for the binary annotations of laughable contexts, which were then categorized into a taxonomy comprising ten categories, including"Empathy and Affinity"and"Humor and Surprise,"highlighting the diverse range of laughter-inducing scenarios. The study also evaluated GPT-4's performance in recognizing the majority labels of laughable contexts, achieving an F1 score of 43.14%. These findings contribute to the advancement of conversational AI by establishing a foundation for more nuanced recognition and generation of laughter, ultimately fostering more natural and engaging human-AI interactions.

Problem

• Laughter Recognition
• Natural Dialogue
• AI Communication

Innovation

• Humor Recognition
• GPT-4
• Natural Human-AI Interaction