Designing Educational Games to Foster Decision Experience in College Innovation and Entrepreneurship Programs

Summary

This study proposes a game-based model using Bayesian networks to enhance innovation and entrepreneurship education, improving knowledge tracking, learning enthusiasm, and adaptability. Results show high accuracy (95.6%) and better outcomes compared to traditional teaching methods.

Abstract

Educational games immerse learners in situational environments to boost engagement, which addresses gaps in monitoring knowledge mastery and sustaining enthusiasm in college Innovation and Entrepreneurship (IE) courses. This study constructs an internal logic mechanism linking IE education and behavior, leveraging Bayesian Networks (BN) for Probabilistic Reasoning (PR) to assess learners' knowledge mastery. Drawing on educational game frameworks for knowledge structure tracking, it proposes a college IE decision-experience game model enhanced by an improved Deep Knowledge Tracing (DKT) algorithm (integrating feature embedding and attention mechanisms). Results show the model's entrepreneurship education score and prediction accuracy both reach 95.6% (the highest among tested models), with all evaluation scale items demonstrating strong information coverage. Average indicator scores exceed 4, reflecting effective feedback. Students' adaptability to the game-based model is 2%-11% higher than to traditional teaching. The embedded real-time evaluation aligns learning performance with instructional goals, enabling strategy adjustment. IE education's value lies in fostering entrepreneurial awareness, capability, and willingness, while its function enhances practical skills like resource integration. The model improves learning enthusiasm, adaptability, and efficiency, offering insights for personalized college IE education design.

Introduction

Innovation and entrepreneurship (IE) education aims to cultivate talents with entrepreneurial literacy and pioneering personalities, focusing on phased training of innovative thinking and entrepreneurial capabilities. However, current IE education lacks practicality and interactive curricula, relying heavily on theory while neglecting hands-on problem-solving skills. Educational games-with high interactivity and scenario simulation-can address this gap by fostering decision-making and teamwork, making them a promising tool for personalized IE learning¹.

To improve IE teaching efficiency, prior studies have integrated....

Protocol

This study was approved by the Shaoxing University Human Research Ethics Committee (Approval No. SU-2023-IE-058). All participants provided written informed consent prior to data collection. The experiment was conducted in accordance with the Declaration of Helsinki (2013).

Game design for the decision experience of IE education for college students

The research implemented a Bayesian Network (BN) for real-time assessment of learners' knowledge mastery. Each knowledge point was modeled as a node with Conditional Probability Tables (CPTs) defining dependencies. Student performance data from ga....

Results

The experiment was based on Karen and Hodhod's educational game evaluation scale, and appropriate evaluation dimensions and items were organized and selected for adjustment. Karen and Hodgod's scale has high authority and applicability in the field of educational games, covering multiple key dimensions of educational games, such as gameplay, pedagogical, interactive, etc. By introducing and adapting this scale, it can more fully and accurately assess the performance of the designed college students' IE educat.......

Discussion

The success of the college IE decision experience game model hinges on critical protocol steps, particularly the integration of BN reasoning for real-time knowledge diagnosis and the improved Deep Knowledge Tracing (DKT-FA) model's feature embedding and AMs. BN's precise CPT initialization-grounded in expert interviews and iteratively updated with student behavior data-ensured accurate identification of weak knowledge links, while DKT-FA's inclusion of answer attempts and help-seeking frequency as features en.......

Materials

List of materials used in this article

Name	Company	Catalog Number	Comments
Adam	Built-in in TensorFlow 2.8.0	Learning rate 0.001
BinaryCrossentropy	Built-in in TensorFlow 2.8.0	Default parameters
C#	Unity 2021.3.8f1 default version	Called through the Unity C# API
CUDA	11.2	It is compatible with TensorFlow 2.8.0
Joint Tree (JT)	pgmpy 0.1.20 is implemented	moralize=True, min-fill triangulation
LabelEncoder	Built-in in scikit-learn 1.0.2	Shared with scikit-learn
ModelCheckpoint	TensorFlow 2.8.0 callback	Based on the validation set AUC
NumPy	Not specified (the latest stable version is acceptable)	Python 3.9.7 environment
pandas	Not specified (the latest stable version is acceptable)	Python 3.9.7 environment
pgmpy	0.1.20	Python 3.9.7 environment
Python	3.9.7	A unified back-end operating environment
scikit-learn	1.0.2	RRID: SCR_002577
SPSS	25	RRID: SCR_002815
TensorFlow	2.8.0	The GPU version requires CUDA 11.2 support
Unity	2021.3.8 f1	RRID: SCR_018230