Gao Yanan, Zhang Jinxi, He Zhonghui, Zhou Zhixiong
School of Physical Education and Sport Science, Fujian Normal University, Fuzhou, China.
Institute of Artificial Intelligence in Sports, Capital University of Physical Education and Sports, 11 Beisanhuan West Road, Beijing, 100191, China, 86 13552505679.
JMIR Serious Games. 2025 Mar 24;13:e65498. doi: 10.2196/65498.
Physical activity (PA) is vital for physical and mental health, but many college students fail to meet recommended levels. Artificial intelligence (AI)-powered gamification interventions through mobile app have the potential to improve PA levels among Chinese college students.
This study aimed to assess the feasibility and usability of an AI-powered gamification intervention.
A quasi-experimental study spanning 2 months was conducted on a sample of college students aged 18 to 25 years old from 18 universities in Beijing. PA data were recorded using the ShouTi Fitness app, and participant engagement was evaluated through surveys. User satisfaction was gauged through the System Usability Scale, while the intervention's feasibility was assessed through Spearman rank correlation analysis, Mann-Whitney tests, and additional descriptive analyses.
As of July 2023, we enrolled 456 college students. In total, 18,073 PA sessions were recorded, with men completing 8068 sessions and women completing 10,055 sessions. The average PA intensity was 7 metabolic equivalent of energy (MET)s per session. Most participants preferred afternoon sessions and favored short-duration sessions, with men averaging 66 seconds per session and women 42 seconds. The System Usability Scale score for the intervention based on app is 65.2. Users responded positively to the integration of AI and gamification elements, including personalized recommendations, action recognition, smart grouping, dynamic management, collaborative, and competition. Specifically, 341 users (75%) found the AI features very interesting, 365 (80%) were motivated by the gamification elements, 364 (80%) reported that the intervention supported their fitness goals, and 365 (80%) considered the intervention reliable. A significant positive correlation was observed between the duration of individual PA and intervention duration for men (ρ=0.510, P<.001), although the correlation was weaker for women (ρ=0.258, P=.046). However, the frequency of PA declined after 35 days.
This study provides pioneering evidence of the feasibility and usability of the AI-powered gamification intervention. While adherence was successfully demonstrated, further studies or interventions are needed to directly assess the impact on PA levels and focus on optimizing long-term adherence strategies and evaluating health outcomes.
体育活动对身心健康至关重要，但许多大学生未达到推荐水平。通过移动应用程序进行的人工智能驱动的游戏化干预有可能提高中国大学生的体育活动水平。
本研究旨在评估人工智能驱动的游戏化干预的可行性和可用性。
对来自北京18所大学的18至25岁大学生样本进行了一项为期2个月的准实验研究。使用“瘦体健身”应用程序记录体育活动数据，并通过调查评估参与者的参与度。通过系统可用性量表衡量用户满意度，同时通过斯皮尔曼等级相关分析、曼-惠特尼检验和其他描述性分析评估干预的可行性。
截至2023年7月，我们招募了456名大学生。总共记录了18073次体育活动，男性完成了8068次，女性完成了10055次。每次体育活动的平均强度为7代谢当量能量（MET）。大多数参与者更喜欢下午的活动，并且喜欢短时间的活动，男性每次活动平均66秒，女性平均42秒。基于应用程序的干预的系统可用性量表得分为65.2。用户对人工智能和游戏化元素的整合反应积极，包括个性化推荐、动作识别、智能分组、动态管理、协作和竞争。具体而言，341名用户（75%）认为人工智能功能非常有趣，365名（80%）受到游戏化元素的激励，364名（80%）报告该干预支持他们的健身目标，365名（80%）认为该干预可靠。男性个体体育活动时长与干预时长之间存在显著正相关（ρ=0.510，P<0.001），尽管女性的相关性较弱（ρ=0.258，P=0.046）。然而，35天后体育活动频率下降。
本研究为人工智能驱动的游戏化干预的可行性和可用性提供了开创性证据。虽然成功证明了依从性，但需要进一步的研究或干预来直接评估对体育活动水平的影响，并专注于优化长期依从策略和评估健康结果。
