EUVIMEDEUVIMED entdecken
Crossref

A Deep Neural Network-Based Adaptive Gamification Approach for Virtual Learning

Yi Lin, Jingjing Chen, Feng Chen, Weiquan Wu

IEEE Transactions on Learning Technologies · 2026 · 19 · 566-583

DOI: 10.1109/tlt.2026.3700399 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Learning Technologies, 2026. Verfasst von Yi Lin und 3 weiteren Autor:innen. Die Arbeit nennt 56 Literaturangaben. Gefördert von: program of Study Abroad for Young Scholars, China Scholarship Council, Integrated Research on Efficient Collaborative Technologies for High-Grade Waterway Navigation Resources in the Minjiang River.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gamification learning in virtual reality environments is extensively utilized to stimulate learner motivation and enhance engagement. However, most existing gamification approaches rely on manually predefined rules or static matching, limiting their adaptability to dynamic changes in learning motivation and behaviors throughout the learning process. Accordingly, we propose a deep neural network-based adaptive gamification for virtual learning (DAG-VL) method and integrate it into an instructional objective-oriented virtual learning pedagogical framework to facilitate adaptive gamification. Within this framework, structured instructional activities are designed according to predefined instructional objectives, and learner feedback data drive the adaptive gamification mechanism, which invokes DAG-VL to dynamically optimize gamification element configurations for subsequent activities. By integrating individualized incentives into the learning process, the mechanism strengthens learner autonomy and competence, thereby encouraging active interaction and improving learning outcomes. DAG-VL incorporates Hexad user types (a learner profiling model categorizing learners into six motivational orientations), alongside learning behavioral characteristics and task contextual information as input to train an end-to-end neural network model, enabling the automatic capture of nonlinear relationships between learner characteristics and learning tasks, facilitating dynamic recommendation of gamification elements. Experimental results indicate that DAG-VL exhibits significant advantages in improving academic performance, promoting the practical application of knowledge, and providing a positive user experience. This study offers a reusable framework and implementation pathway for adaptive gamification instructional design in virtual learning.

Förderung

  • program of Study Abroad for Young Scholars
  • China Scholarship Council
  • Integrated Research on Efficient Collaborative Technologies for High-Grade Waterway Navigation Resources in the Minjiang River
  • Fujian Provincial Department of Transportation, China

Zitieren

APA

Lin, Y., Chen, J., Chen, F., & Wu, W. (2026). A Deep Neural Network-Based Adaptive Gamification Approach for Virtual Learning. IEEE Transactions on Learning Technologies, 19, 566-583. https://doi.org/10.1109/tlt.2026.3700399

Vancouver

Lin Y, Chen J, Chen F, Wu W. A Deep Neural Network-Based Adaptive Gamification Approach for Virtual Learning. IEEE Transactions on Learning Technologies. 2026;19:566-583. doi:10.1109/tlt.2026.3700399

BibTeX
@article{Lin2026,
  author = {Lin, Yi and Chen, Jingjing and Chen, Feng and Wu, Weiquan},
  title = {A Deep Neural Network-Based Adaptive Gamification Approach for Virtual Learning},
  journal = {IEEE Transactions on Learning Technologies},
  year = {2026},
  volume = {19},
  pages = {566--583},
  doi = {10.1109/tlt.2026.3700399}
}
Kostenlos starten →