Frontiers in Educational Research, 2026, 9(2); doi: 10.25236/FER.2026.090201.
Suhan Wu1, Min Luo2
1School of Economics and Management, Nanjing Polytechnic Institute, No.188 Xinle Road, Luhe District, Nanjing, 210048, Jiangsu, China
2School of Management, Shenzhen University of Information Technology, Longxiang Road 2188, Shenzhen, 518172, Guangdong, China
The rapid diffusion of large language models has accelerated the uptake of educational chatbots, yet vocational colleges face a distinctive deployment challenge shaped by competence-oriented task chains, heterogeneous instructional settings, and stringent governance requirements. This paper conceptualizes chatbot adoption as an integrated decision problem in which selection and allocation must be determined jointly under binding constraints on budget, infrastructure capacity, faculty workload, and institutional obligations related to privacy, academic integrity, accountability, and auditability. Building on this framing, we develop a governance-aware Hybrid Genetic–Tabu framework that structures decision-making through a feasibility-first explore–refine workflow. Population-based exploration is used to generate diversified admissible selection–allocation plans, while tabu-guided refinement improves promising candidates via interpretable local adjustments and mitigates cycling under hard constraints. The framework further emphasizes traceability by producing an auditable decision artifact that makes decision criteria, binding constraints, and oversight boundaries explicit, thereby supporting cross-unit coordination and iterative adaptation as tools, policies, and instructional needs evolve. The study offers a compact methodology for responsible chatbot deployment in vocational colleges and outlines directions for future work on empirical assessment, preference elicitation, and domain-sensitive extensions for higher-risk training contexts.
Vocational Education; Educational Chatbots; Generative AI Governance; Selection and Allocation; Hybrid Genetic–tabu Framework
Suhan Wu, Min Luo. A Conceptual Hybrid Genetic–Tabu Framework for Chatbot Selection and Allocation in Vocational Colleges. Frontiers in Educational Research (2026), Vol. 9, Issue 2: 1-7. https://doi.org/10.25236/FER.2026.090201.
[1] Kasneci E, Seßler K, Küchemann S, et al. ChatGPT for good? On opportunities and challenges of large language models for education[J]. Learning and Individual Differences, 2023, 103: 102274.
[2] Guthrie H. Competence and competency-based training: What the literature says[M]. ERIC, 2009.
[3] Cotton D R, Cotton P A, Shipway J R. Chatting and cheating: Ensuring academic integrity in the era of ChatGPT[J]. Innovations in Education and Teaching International, 2024, 61(2): 228-239.
[4] Farshidi S, Jansen S, de Jong R, et al. A decision support system for software technology selection[J]. Journal of Decision Systems, 2018, 27(sup1): 98-110.
[5] Glover F, Kelly J P, Laguna M. Genetic algorithms and tabu search: Hybrids for optimization[J]. Computers & Operations Research, 1995, 22(1): 111-134.
[6] Labadze L, Grigolia M, Machaidze L. Role of AI chatbots in education: Systematic literature review[J]. International Journal of Educational Technology in Higher Education, 2023, 20(1): 56.
[7] Okonkwo C W, Ade-Ibijola A. Chatbots applications in education: A systematic review[J]. Computers and Education: Artificial Intelligence, 2021, 2: 100033.
[8] Dong B, Bai J, Xu T, et al. Large language models in education: A systematic review[C]. 2024 6th International Conference on Computer Science and Technologies in Education (CSTE), 2024: 131-134.
[9] Yu Y, Zhao Z. Development of vocational education and training chatbot supported by large language model-based multi-agent system[J]. Vocation, Technology & Education, 2025.
[10] Holmes W, Miao F. Guidance for generative AI in education and research[M]. Unesco Publishing, 2023.
[11] Kofinas A K, Tsay C H H, Pike D. The impact of generative AI on academic integrity of authentic assessments within a higher education context[J]. British Journal of Educational Technology, 2025.
[12] Gundu T. Strategies for e-assessments in the era of generative artificial intelligence[J]. Electronic Journal of e-Learning, 2024, 22(7): 40-50.
[13] Salvado L L, Villeneuve E, Masson D, et al. Decision support system for technology selection based on multi-criteria ranking: Application to NZEB refurbishment[J]. Building and Environment, 2022, 212: 108786.
[14] Wiangkham A, Vongvit R. Comparative analysis of multi-criteria decision making methods for prioritizing influential factors of ChatGPT adoption in higher education[J]. Expert Systems with Applications, 2025: 128188.
[15] Li D, Wang L, Wang M. Genetic algorithm and tabu search: A hybrid strategy[J]. IFAC Proceedings Volumes, 1999, 32(2): 8664-8668.