The modern labor market demands that educational institutions prepare specialists capable of effectively responding to rapidly changing professional standards and technologies. In this regard, the use of innovative approaches to adapt educational programs becomes a key factor. This study is dedicated to developing a methodology for using heterogeneous knowledge graphs to create a recommendation system aimed at bridging the gap between existing educational courses and the dynamically changing requirements of the labor market. The central element of the study is the use of knowledge graphs to aggregate and analyze diverse data on skills, job vacancies, and educational courses. Knowledge graphs not only structure large volumes of information but also visualize complex connections between various educational modules and professional requirements. This approach fosters a deeper understanding of how educational programs can be adjusted to best match market specifics. An important aspect of the study is the application of multilingual semantic similarity algorithms to analyze and match skills. These algorithms play a key role in determining the degree of correspondence between the skills listed in educational programs and courses and those required for specific job vacancies. The use of natural language processing techniques allows not only to capture explicit keyword matches but also to recognize deep semantic connections, which is an integral part of accurate matching in educational and professional domains. The results of the study demonstrate that the proposed methodology can effectively analyze multilingual relationships between educational and professional skills, which improves personalized course and job recommendations. Our study contributes to the literature by proposing a new methodology for building recommendations that improves the accuracy of personalized educational and career recommendations and facilitates the adaptation of educational programs to dynamic changes in the labor market.
This article addresses the task of building personalized educational recommendations based on a heterogeneous knowledge graph that integrates data from university curricula, job vacancies, and online courses. To solve the problem of course recommendations by their relevance to a user’s competencies, a graph neural network (GNN)-based approach is proposed, specifically utilizing and comparing the Heterogeneous Graph Transformer (HGT) architecture, Graph Sample and Aggregate network (GraphSAGE), and Heterogeneous Graph Attention Network (HAN). Experiments were conducted on a heterogeneous graph comprising various node and relation types. The models were evaluated using regression and ranking metrics. The results demonstrated the superiority of the HGT-based recommendation model as a link regression task, especially in terms of ranking metrics, confirming its suitability for generating accurate and interpretable recommendations in educational systems. The proposed approach can be useful for developing adaptive learning recommendations aligned with users’ career goals.
22 September 2026 in Herald of the Kazakh-British technical university
The article presents the development of an integration model based on knowledge graphs and machine learning methods for analyzing relationships between educational programs, labor market requirements, and online courses (MOOCs). The relevance of the study is driven by rapid changes in the information technology sector, which lead to a mismatch between graduate competencies and employer expectations. To reduce this gap, a heterogeneous knowledge graph integrating data from university curricula, job vacancies, and online courses is proposed. The model implements a meta-path connecting skills, job requirements, and learning courses, enabling recommendations for educational and career development for different categories of users. Multilingual transformers were applied to process textual descriptions in Russian and English. The data sources include competency maps of educational programs, job postings from the hh.kz platform, and courses from Coursera, all integrated into the Neo4j graph database. The obtained results demonstrate the capability to identify missing competencies and automatically recommend relevant courses for their acquisition. The proposed model can be applied in curriculum design, development of learning trajectories, and decision-making support within educational environments.
One of the traditional methods for community detection in knowledge graphs is agglomerative clustering. Agglom-erative hierarchical clustering is a widely used type of hierarchical clustering for grouping objects based on their similarity. This method follows a bottom-up approach, beginning with each individual data point considered as an independent cluster, which are then continuously merged based on a similarity threshold between clusters. This paper focuses on the use of agglomerative clustering for analyzing skills extracted from job postings on an online recruitment platform. It describes the approach to data collection, processing, and subsequent clustering, providing an overview of linkage methods between clusters and examples of the application of various coefficients for quantitative assessment of cluster quality. An analysis of bilingual clusters in Russian and English is conducted, al-lowing for an evaluation of the versatility and adaptability of the proposed approach to analyzing the multilingual labor market in Kazakhstan. It was found that agglomerative clustering methods hold significant potential for identi-fying structured groups of skills, which can enhance the understanding of labor market trends and needs. The analysis of clusters formed in different languages confirmed the universality and adaptability of the proposed ap-proach to multilingual data.