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

TL;DR

<3-5 sentence high-level summary>

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.

Figures (5)

• Figure 1: A screenshot from Jouzu featuring the in-text word inspector. The image shows a sent user message with the translation, "What are you going to do today?" and a response from the character Kitsune. The user has tapped on the sentence, and the flashcard for the Japanese word "shizen," translated to "nature" in English, appears with the furigana, English definition, and romaji spelling of the word.
• Figure 2: Mean participant ratings by experience category with standard deviation error bars (Likert scale: 1–5).
• Figure 3: Mean group ratings for Chinese vs. non-Chinese native speakers. The left bars (blue) represent native Chinese speakers, and the right bars (orange) represent non-Chinese native speakers.
• Figure 4: Mean group ratings by Japanese proficiency level. From left to right, the bars represent complete beginner — i.e., the user has had no exposure to Japanese — (blue), beginner level (orange), intermediate level (green), and native or near-native level (red).
• Figure 5: Heatmap of mean experience ratings across Japanese proficiency levels. Darker shades indicate higher user satisfaction per category.