Topic mining for theses and job ads in ICT sector: can higher education institutes respond to job market demands?
Kauttonen, Janne; Ali Khan, Umair; Aunimo, Llil; Nyqvist, Antti; Klemetti, Aarne (2024)
Frontiers Media S.A.
2024
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2024050325446
https://urn.fi/URN:NBN:fi-fe2024050325446
Tiivistelmä
Introduction: This study aims to tackle the challenge of ensuring higher education students are equipped with high-demand skills for today’s job market. The focus is on aligning the knowledge acquired during their studies, as represented by final-year thesis projects, with the skills and topics specified in actual job advertisements.
Methods: We developed a computational framework that uses automated subject indexing to extract representative skills and topics from two major datasets: thesis abstracts from Information and Communication Technology (ICT) programmes of Finnish Universities of Applied Sciences, and ICT-related job ads from a top Finnish job portal. Our dataset spans 12 years, comprising 18,254 theses and 107,335 ads. The framework includes a subject indexing model for keyword extraction, dimension reduction techniques for data simplification, clustering algorithms to group similar items, and correlation analysis to compare similarities and differences between the two datasets.
Results: The analysis uncovered both similarities and differences between thesis topics and trends in job ads. It highlighted areas where education aligns with industry demands but also pointed out existing gaps.
Discussion: Our framework not only helps to align the education provided with industry demands but also ensures that higher education institutes can stay up-to-date with the latest skills and knowledge in the field, thereby better equipping students for success in their careers. While the framework was applied to the ICT sector in this instance, its design allows expansion into other fields offering a data-informed approach for continuous development of teaching curricula and methodologies.
Methods: We developed a computational framework that uses automated subject indexing to extract representative skills and topics from two major datasets: thesis abstracts from Information and Communication Technology (ICT) programmes of Finnish Universities of Applied Sciences, and ICT-related job ads from a top Finnish job portal. Our dataset spans 12 years, comprising 18,254 theses and 107,335 ads. The framework includes a subject indexing model for keyword extraction, dimension reduction techniques for data simplification, clustering algorithms to group similar items, and correlation analysis to compare similarities and differences between the two datasets.
Results: The analysis uncovered both similarities and differences between thesis topics and trends in job ads. It highlighted areas where education aligns with industry demands but also pointed out existing gaps.
Discussion: Our framework not only helps to align the education provided with industry demands but also ensures that higher education institutes can stay up-to-date with the latest skills and knowledge in the field, thereby better equipping students for success in their careers. While the framework was applied to the ICT sector in this instance, its design allows expansion into other fields offering a data-informed approach for continuous development of teaching curricula and methodologies.