{"title":"Enhancing textile heritage engagement through generative AI-based virtual assistants in virtual reality museums","authors":"Pakinee Ariya , Songpon Khanchai , Kannikar Intawong , Kitti Puritat","doi":"10.1016/j.cexr.2025.100112","DOIUrl":null,"url":null,"abstract":"<div><div>This study investigates how generative AI-based virtual assistants embedded within immersive virtual reality (VR) environments can enhance user engagement and cultural learning in virtual museums. Situated at the Wieng Yong House Museum in Thailand, the research addresses the challenge of preserving and promoting textile heritage in the digital age. The study aims to design, implement, and evaluate an AI-driven virtual docent capable of delivering personalized, multilingual, and real-time cultural information through interactive voice-based engagement. Using a purposive sampling technique, 25 university students participated in a convergent parallel mixed-methods study combining structured questionnaires and open-ended feedback. Quantitative findings from structured questionnaires revealed high user satisfaction, with mean scores of 4.40 for visual quality and 4.20 for ease of interaction, while response latency and voice clarity received lower ratings of 3.36 and 3.62 respectively, indicating areas for improvement. Qualitative analysis revealed four key themes: user experience with the system, communication quality, response effectiveness, and suggestions for improvement. The results demonstrate both the transformative potential and current limitations of generative AI in digital heritage settings. This study contributes to the development of more inclusive and engaging virtual museum experiences for the teaching and learning of cultural heritage, offering practical design insights for educators, curators, and developers.</div></div>","PeriodicalId":100320,"journal":{"name":"Computers & Education: X Reality","volume":"7 ","pages":"Article 100112"},"PeriodicalIF":0.0000,"publicationDate":"2025-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Education: X Reality","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2949678025000200","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
This study investigates how generative AI-based virtual assistants embedded within immersive virtual reality (VR) environments can enhance user engagement and cultural learning in virtual museums. Situated at the Wieng Yong House Museum in Thailand, the research addresses the challenge of preserving and promoting textile heritage in the digital age. The study aims to design, implement, and evaluate an AI-driven virtual docent capable of delivering personalized, multilingual, and real-time cultural information through interactive voice-based engagement. Using a purposive sampling technique, 25 university students participated in a convergent parallel mixed-methods study combining structured questionnaires and open-ended feedback. Quantitative findings from structured questionnaires revealed high user satisfaction, with mean scores of 4.40 for visual quality and 4.20 for ease of interaction, while response latency and voice clarity received lower ratings of 3.36 and 3.62 respectively, indicating areas for improvement. Qualitative analysis revealed four key themes: user experience with the system, communication quality, response effectiveness, and suggestions for improvement. The results demonstrate both the transformative potential and current limitations of generative AI in digital heritage settings. This study contributes to the development of more inclusive and engaging virtual museum experiences for the teaching and learning of cultural heritage, offering practical design insights for educators, curators, and developers.