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

TL;DR

This paper investigates laughter in Japanese spontaneous conversations by annotating laughable contexts, creating a taxonomy of reasons, and evaluating AI's ability to recognize such contexts, aiming to improve human-AI interaction naturalness.

Contribution

It introduces a novel annotation process and taxonomy for laughable contexts in dialogue, and assesses AI performance in recognizing these contexts.

Findings

Developed a taxonomy with 10 categories for laughable contexts.

Achieved an F1 score of 43.14% in AI recognition of laughable contexts.

Provided insights into diverse laughter-inducing scenarios in dialogue.

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-4o'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.