From Performers to Creators: Understanding Retired Women's Perceptions of Technology-Enhanced Dance Performance

TL;DR

This study addresses how to make technology-assisted dance more accessible for China’s large population of retired women by designing age-sensitive AI mediation. Through two co-design workshops, StageTailor combines LLM-based scene generation, text-to-video synthesis, and motion-capture-driven visual effects to enable pre-production co-creation and on-stage embodiment. Findings show that low-barrier keyword prompts, context-aware visuals, and participatory scaffolds empower dancers to become co-creators with strong ownership over their stage aesthetics, while also revealing gaps in narrative nuance and seamless integration. The work contributes design implications and a taxonomy for age-sensitive AIGC in cultural practice, with potential broader impact on aging creativity and community-based arts.

Abstract

Over 100 million retired women in China engage in dance, but their performances are constrained by limited resources and age-related decline. While interactive dance technologies can enhance artistic expression, existing systems are largely inaccessible to non-professional older dancers. This paper explores how interactive dance technologies can be designed with an age-sensitive approach to support retired women in enhancing their stage performance. We conducted two workshops with community-based retired women dancers, employing interactive dance and LLM-powered video generation probes in co-design activities. Findings indicate that age-sensitive adaptations, such as low-barrier keyword input, motion-aligned visual effects, and participatory scaffolds, lowered technical barriers and fostered a sense of authorship. These features enabled retired women to empower their stage, transitioning from passive recipients of stage design to empowered co-creators of performance. We outline design implications for incorporating interactive dance and artificial intelligence-generated content (AIGC) into the cultural practices of retired women, offering broader strategies for age-sensitive creative technologies.

Figures (7)

• Figure 1: Procedure of the Workshop I with 15 participants divided into four groups (3-4 participants per group) to understand retired women’s perspectives on current stage performances and interactive dance. The study followed a four-phase structure: (i) a preliminary questionnaire and background interview; (ii) an introduction to interactive dance concepts; (iii) a hands-on experience with interactive dance probes; (iv) a concluding group discussion to synthesize their experiences and ideas.
• Figure 2: Example scenes from real-world performances illustrating common issues with current stage backdrops in retired women's dance. These backdrops are usually selected by group leaders from online videos or static images that loosely match the dance theme or regional style (e.g., grasslands for Xinjiang dances, classical paintings for fan dances). In some cases, participants attempt to manually stitch together regional photos for promotional purposes, though with limited tools and skills.
• Figure 3: Workflow of StageTailor, a two-step background creation tool designed for retired dancers. In Step 1, users describe a desired scene using keywords, which are expanded by LLM and used to generate a background video via AI text-to-video synthesis. In Step 2, users record their dance movements and select motion-responsive visual effects from a system library. These effects are synchronized with the movements and integrated into the generated video.
• Figure 4: Several example interfaces of Stagetailor: (a) AI Scene Generation Interface, allowing users to input keywords for automated video scene creation, with options for direct generation or stepwise refinement. (b) Interaction Mode Selection, offering body-motion and prop-based control schemes, including a 4s calibration countdown. (c) Dance Effects Recording Panel, featuring real-time motion capture, visual effect presets, and terminal feedback for seamless creative iteration.
• Figure 5: Process of Workshop II with 16 participants divided into four groups (4 participants per group) to evaluate the usability, usefulness, and experiential value of StageTailor. The study followed a four-phase structure: (i) Study Introduction, (ii) Tool Introduction and Demonstration, (iii) Participant Hands-On Experience, and (iv) Questionnaires and In-Depth Interviews.