Technology Category
Machine Learning: Structured LearningApplication Domains: Humanities & Computational Social ScienceData Mining & Knowledge Management: Semantic Web
Quantifying the influence of Vocational Education and Training with text embedding and similarity-based networks
🤖 AI Summary
Quantifying the real-world impact of Vocational Education and Training (VET) programs on employment and skill development has long been hindered by ambiguous linkages among courses, occupations, and skills. To address this, we construct a tripartite heterogeneous similarity network—integrating courses, occupations, and skills—using Sentence Transformer–based text embeddings, enabling, for the first time, large-scale VET impact attribution across >17,000 nodes. Our method innovatively combines semantic embedding with multilayer network modeling, employing cosine similarity to quantify cross-entity associations. Results reveal that course impact intensity is strongly contingent on skill specificity; courses in manufacturing and digital technologies exhibit significantly greater forward-looking relevance; conversely, VET supply is disproportionately concentrated in generic-skill occupations (e.g., administration and services), exposing structural misalignment between training provision and labor market demand. This work establishes an interpretable, scalable evaluation framework for evidence-based VET policy design and skill ecosystem governance amid the Fourth Industrial Revolution.
Technology Category
Application Category
📝 Abstract
Assessing the potential influence of Vocational Education and Training (VET) courses on creating job opportunities and nurturing work skills has been considered challenging due to the ambiguity in defining their complex relationships and connections with the local economy. Here, we quantify the potential influence of VET courses and explain it with future economy and specialization by constructing a network of more than 17,000 courses, jobs, and skills in Singapore's SkillsFuture data based on their text similarities captured by a text embedding technique, Sentence Transformer. We find that VET courses associated with Singapore's 4th Industrial Revolution economy demonstrate higher influence than those related to other future economies. The course influence varies greatly across different sectors, attributed to the level of specificity of the skills covered. Lastly, we show a notable concentration of VET supply in certain occupation sectors requiring general skills, underscoring a disproportionate distribution of education supply for the labor market.
Problem
Research questions and friction points this paper is trying to address.
Quantify VET courses' influence on job opportunities and skills
Analyze VET impact across sectors using text embedding networks
Identify disproportionate VET supply distribution in labor market
Innovation
Methods, ideas, or system contributions that make the work stand out.
Text embedding with Sentence Transformer
Similarity-based network construction
Quantifying VET course influence
🔎 Similar Papers
No similar papers found.
