Animating Language Practice: Engagement with Stylized Conversational Agents in Japanese Learning

TL;DR

This paper presents Jouzu, a stylized anime-inspired conversational agent for Japanese language learning, which enhances learner engagement and expressive practice through culturally grounded design and expressive speech.

Contribution

It introduces a novel stylized conversational agent integrating large language models and expressive speech, demonstrating increased engagement and expressive language use in real-world learning settings.

Findings

Participants interacted frequently and creatively.

Advanced learners used more expressive forms.

Stylization increased enjoyment and experimentation.

Abstract

We explore Jouzu, a Japanese language learning application that integrates large language models with anime-inspired conversational agents. Designed to address challenges learners face in practicing natural and expressive dialogue, Jouzu combines stylized character personas with expressive text-to-speech to create engaging conversational scenarios. We conducted a two-week in-the-wild deployment with 52 Japanese learners to examine how such stylized agents influence engagement and learner experience. Our findings show that participants interacted frequently and creatively, with advanced learners demonstrating greater use of expressive forms. Participants reported that the anime-inspired style made practice more enjoyable and encouraged experimenting with different registers. We discuss how stylization shapes willingness to engage, the role of affect in sustaining practice, and design opportunities for culturally grounded conversational AI in computer-assisted language learning (CALL). By framing our findings as an exploration of design and engagement, we highlight opportunities for generalization beyond Japanese contexts and contribute to international HCI scholarship.