Back to search

National Technical University of Athens (NTUA)

Συστήματα συστάσεων για τη γεφύρωση του χάσματος δεξιοτήτων μεταξύ αγοράς εργασίας και εκπαίδευσης στον τομέα της τεχνολογίας

Abstract

dc:description

In the last few years technology evolves rapidly, and as a result, the same applies to technology-related professions, concerning the need for specific skills. On the other hand, technological educational institutions oftentimes have difficulties to keep track and align with the labour market needs. Consequently, they sometimes end up teaching skills that are considered obsolete. Regarding students and lifelong learners, an important objective is to avoid courses that teach such skills, as they aim at landing a job in which they will utilise the skills they have acquired during their studies. Furthermore, with regards to educational institutions, an important challenge is to comply with the labour market needs, by providing courses that can be useful for the career of their students. In this context, this dissertation’s main objective is to bridge the gap between the skills taught by educational institutions and the ones required by the labour market in the technology sector, through the use of state-of-the-art data analytics techniques, including data mining, recommender systems and natural language processing. Specifically, in this dissertation, several studies and solutions that have already been proposed are examined in depth. As a next step, a skill and course recommender system has been developed for students and lifelong learners, in order to help them select courses that will improve their skills in accordance with the labour market needs. Additionally, a curriculum redesign recommender system has been developed for professors and educational institutions, for the evaluation and improvement of their organisation’s curriculum, to be compliant with the needs of the labour market. These recommender systems along with their methodology have been applied in the Greek labour market and the sector of software engineering, and the results prove to be very promising. The proposed methodology and services can be applied with little to no modifications to other sectors as well. It is worth mentioning that during the design and development phase of the aforementioned services, several additional problems have emerged. These problems and their solutions are also part of this dissertation. Specifically, this dissertation also deals with the problem of fairness among providers in recommender systems in terms of coverage and diversity in users for each provider’s items. This problem is modeled as an optimisation problem in literature, and it is an NP-complete problem. To this end, we developed a heuristic algorithm with polynomial computational complexity that finds solutions very close to the optimal one, as illustrated in the experimental results. In addition, the problem of recommender system operation and particularly their ethical implications to users is thoroughly examined in this dissertation. In this context, several widely known recommender systems were analysed and proved to be ethically problematic. To this end, we propose a series of regulatory actions. Their goal is the betterment of the recommender systems’ function and the harmonisation of their progress with social prosperity.

Degree

thesis:*
Grantor dc:publisher
National Technical University of Athens (NTUA)
Year dc:date
2023

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Karakolis, Evangelos
  • Καρακόλης, Ευάγγελος

Subjects

dc:subject × 22

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/55192

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Karakolis, Evangelos; Καρακόλης, Ευάγγελος. Συστήματα συστάσεων για τη γεφύρωση του χάσματος δεξιοτήτων μεταξύ αγοράς εργασίας και εκπαίδευσης στον τομέα της τεχνολογίας. National Technical University of Athens (NTUA), 2023. http://hdl.handle.net/10442/hedi/55192