Artificial intelligence (AI), virtual reality (VR), and exergame technologies have been increasingly used in dance and movement activities. However, this literature remains dispersed across different areas, making it difficult to determine how the field has developed. This study mapped the research landscape and thematic development of AI-, VR-, and exergame-based dance and movement research on psychological outcomes using bibliometric analysis and latent Dirichlet allocation (LDA) topic modeling. A total of 252 records indexed in the Web of Science Core Collection from 2011 to 2025 were included. Five related thematic strands were identified: immersive dance interaction and technology-supported teaching; rehabilitation-oriented dance or rhythm training; school-based exergaming and psychophysiological assessment; behavioral program design and intervention implementation; and AI-based motion or emotion recognition. These strands indicate that the field has developed into a multi-layered research space shaped by technology functions, movement contexts, intervention formats, and psychological constructs, rather than a single dance-intervention or technology-application domain. At the same time, psychological outcomes were not represented with equal clarity across these strands. Participation-related and psychosocial constructs, including enjoyment, motivation, engagement, self-efficacy, social interaction, emotional expression, and quality of life, were more frequently represented, whereas mental-health-related outcomes such as anxiety, depression, stress, loneliness, and psychological well-being were less consistently connected to technology-supported dance or movement interventions. These findings clarify where evidence is concentrated, how major themes are organized, and where psychological outcome measurement requires clearer theoretical and methodological specification. Future studies should use comparative and longitudinal designs to examine whether VR/AI-based feedback-supported movement training offers added value over conventional dance or movement programs for psychological outcomes, participation, exercise experience, and longer-term behavior change.

Objective assessment of technical execution in artistic gymnastics remains challenging because scoring relies on expert visual judgement of posture, movement control, alignment, symmetry, and action-specific execution quality. This study developed a markerless, video-based, and biomechanically interpretable machine learning framework for estimating gymnastics execution scores from pose-derived movement features. A total of 500 men’s artistic gymnastics floor-element video sequences were collected under controlled conditions and independently scored by three FIG-certified judges, with the mean score used as the ground-truth label. Pose trajectories were extracted using MediaPipe Pose, and judging-relevant landmarks were retained to represent key body segments. After hip-centred coordinate normalisation, biomechanical features were constructed from four groups: position magnitude, joint angle, temporal velocity, and left–right symmetry. As the core prediction method, this study proposes a Biomechanical Feature-Group Attention Support Vector Regression model (BFG-AttSVR). BFG-AttSVR introduces an action-specific feature-group attention mechanism to learn different group-level importance weights for different gymnastics actions. Within BFG-AttSVR, the attention weights are learned through a two-stage optimisation strategy, including data-driven initialisation based on cross-validated Ridge regression and gradient-free fine-tuning using an RBF-kernel SVR objective. Experimental results showed that BFG-AttSVR achieved an MAE of 0.0465 ± 0.0041, an RMSE of 0.0621 ± 0.0074, and an $R^2$ of 0.9710 ± 0.0131, outperforming the strongest SVR (RBF) baseline with an RMSE of 0.0743 ± 0.0071. The proposed framework provides a low-cost, objective, and interpretable approach for video-based gymnastics score estimation.

Artificial intelligence (AI) has rapidly reshaped sports motion analysis through advances in wearable sensing, computer vision, and deep learning. However, existing reviews often focus on isolated techniques and lack a systematic evolutionary perspective. This study presents a 15-year bibliometric and evolutionary review of AI in sports motion analysis (2011–2025), integrating scientometric mapping with quantitative content analysis across modalities, methods, and applications. A comprehensive multi-source dataset of 2602 publications was analyzed using VOSviewer and CiteSpace to examine knowledge structures, collaboration patterns, co-citation networks, and emerging research fronts. In addition, each study was categorized by modality (wearable, visual, and multi-modal), AI method (traditional machine learning, deep learning, and transformer-based), and task type (activity recognition, performance analysis, rehabilitation, and others). The results reveal exponential growth and a clear three-stage evolution: a sensor-driven phase dominated by wearable devices and traditional machine learning (2011–2015), a deep learning expansion phase centered on vision-based modeling (2016–2019), and a recent deep learning consolidation phase characterized by emerging transformer-based methods, increasing multimodal integration, real-time monitoring, and application-oriented sports analytics (2020–2025). The field has shifted from signal-based recognition toward vision-centered performance evaluation, rehabilitation-related movement assessment, and injury-informed applications. This data-driven review provides an integrated evolutionary framework and future research roadmap to support the continued development of AI-driven analytics in sports science, athlete monitoring, and health-related human movement analysis.