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

Danlin Zheng, Xiaoying Wei+5 more|arXiv (Cornell University)|Jan 31, 2026

Social Robot Interaction and HRI0 citations

TL;DR

The study designs age-sensitive interactive dance tools for retired Chinese women, enabling co-creation of stage visuals through LLM-driven scene generation and AI video synthesis, validated via two workshops.

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.

Motivation & Objective

• Motivate design of accessible, age-sensitive technologies to support retired women in moving from passive participants to co-creators of stage performances.
• Investigate how interactive dance technologies can be adapted to address resource constraints and age-related changes in this population.
• Examine how AI-generated content and conversational interfaces influence creative agency and collaboration in community dance.
• Develop and evaluate the StageTailor system integrating LLM-based scene generation, AI video synthesis, and motion capture for real-time effects.

Proposed method

• Two workshops with retired women dancers (Workshop I: 15 participants; Workshop II: 16 participants) using co-design probes and StageTailor.
• Co-design activities informed by a taxonomy of interactive dance types derived from a literature review.
• StageTailor combines large language models for scene generation, AI video synthesis for backgrounds, and motion capture for real-time effects.
• Data collected through questionnaires, interviews, observations, and semi-structured focus groups, analyzed with reflexive thematic analysis.
• Iterative design and evaluation of age-sensitive adaptations and participatory scaffolds (e.g., low-barrier keyword input, motion-aligned visuals).

Figure 1 . (a) A traditional stage setup for retired women’s dance performances, using generic, static backdrops.(b) Our probe in workshop II, StageTailor, enables dynamic co-creation: artificial intelligence (AI) generates semantically aligned backgrounds from keywords, while motion-triggered effec

Experimental results

Research questions

• RQ1 RQ1: How can interactive dance technologies be designed in an age-sensitive way to support retired women under resource and aging constraints in enhancing stage performance?
• RQ2 RQ2: How can AIGC and LLM-powered input be integrated into interactive dance systems to lower technical barriers and foster creative participation among retired women?

Key findings

• Age-sensitive adaptations such as low-barrier keyword input and motion-aligned visuals lowered cognitive barriers and fostered authorship.
• Participants responded positively to AI-generated outputs but desired richer control over temporal, emotional, and stylistic nuances.
• Interactive visual effects were enthusiastically received, yet participants sought better contextual integration and stylistic coherence with narratives.
• Overall, co-creative experiences were perceived positively, shifting participants from consumers to empowered co-creators with a stronger sense of ownership.
• Findings support a design framework—Age-Sensitive Creative AI Mediation—for redistributing aesthetic control to older adults in stage performance.

Figure 2 . 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