Research on Students' Satisfaction of Intelligent Learning Based on Text Mining Technology

Area of Science:

• Business Education
• Information Technology in Education
• Curriculum Development

Background:

• Growing demand for information technology and data analytics skills in professional fields.
• Educators are integrating technology into curricula to meet industry needs.
• Student satisfaction is a critical metric for evaluating curriculum effectiveness.

Purpose of the Study:

• To explore undergraduate students' perceptions of intelligent curriculum teaching content and approaches.
• To analyze student satisfaction with technology-enhanced business education.
• To identify areas for curriculum improvement and teaching design optimization.

Main Methods:

• Text mining technologies including TFIDF analysis, topic modeling, and sentiment analysis.
• Analysis of student summary texts from a Chinese university's curriculum learning.
• Quantitative analysis of perceptions from 51 second-year undergraduate students.

Main Results:

• Students reported higher satisfaction with financial sharing center content compared to Robotic Process Automation (RPA) financial robots.
• Students adjusted better to case analysis and flipped classroom teaching methods than simulation training or traditional lecturing.
• Identified specific content areas and teaching approaches that positively influence student satisfaction.

Conclusions:

• Findings provide actionable insights for business program leaders and educators.
• Recommendations for enhancing teaching content and optimizing teaching design to boost student satisfaction.
• Emphasizes the importance of aligning curriculum with student preferences for effective technology integration.