An Effective Evaluation Method of College Students’ Innovation and Entrepreneurship Education Based on Data Mining Algorithm
Year: 2025
Type: article
Abstract: In the evolving landscape of higher education, accurately assessing the impact of Innovation and Entrepreneurship (IE) education on college students is crucial. This study introduces a novel approach that leverages Transformer and BERT models to evaluate the educational outcomes effectively. The methodology begins with rigorous preprocessing of extensive textual data sourced from students’ submissions, including project proposals, reflective essays, and discussion forum contributions. At its core, the approach integrates the capabilities of Transformer and BERT models, combining their strengths in deep contextual understanding and nuanced feature extraction. This hybrid model enables a more advanced assessment of students’ innovative thinking and entrepreneurial skills. The evaluation is further refined using a series of metrics designed to measure various dimensions of IE education, such as creativity, problem-solving, market analysis, and business acumen. Comparative experimental results demonstrate that the proposed hybrid model significantly outperforms traditional assessment methods across multiple metrics, offering a more comprehensive and accurate understanding of the effectiveness of IE education in higher education institutions.
Authors: Zhiyao Liu, Aiping Cui
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Quality education
Open Access status: hybrid
OpenAlex ID: W4408007226