This section promotes external academic papers, articles or reports using ESCO in their methodology or presenting ESCO in the European and International context.
As ESCO becomes increasingly used in applications and research projects across Europe and beyond, it is valuable to collect such sources and share best practices by diverse stakeholders. Therefore this section strengthens the sharing of knowledge within the ESCO community, and can contribute to mutual learning in the field of skills, occupations and qualifications among European and international actors.
If you are interested in sharing your publication, please write to EMPL-ESCO-SECRETARIAT@ec.europa.eu.
Authors: Mike Zhang, Kristian Nørgaard Jensen, Sif Dam Sonniks, Barbara Plank
Skill Extraction (SE) is an important and widely-studied task useful to gain insights into labor market dynamics. However, there is a lacuna of datasets and annotation guidelines; available datasets are few and contain crowd-sourced labels on the span-level or labels from a predefined skill inventory. To address this gap, we introduce SKILLSPAN, a novel SE dataset consisting of 14.5K sentences and over 12.5K annotated spans. We release its respective guidelines created over three different sources annotated for hard and soft skills by domain experts. We introduce a BERT baseline (Devlin et al., 2019). To improve upon this baseline, we experiment with language models that are optimized for long spans (Joshi et al., 2020; Beltagy et al., 2020), continuous pre-training on the job posting domain (Han and Eisenstein, 2019; Gururangan et al., 2020), and multi-task learning (Caruana, 1997). Our results show that the domain-adapted models significantly outperform their non-adapted counterparts, and single-task outperforms multi-task learning.
Authors: Mike Zhang, Kristian Nørgaard Jensen, Barbara Plank
Skill Classification (SC) is the task of classifying job competences from job postings. This work is the first in SC applied to Danish job vacancy data. We release the first Danish job posting dataset: Kompetencer (en: competences), annotated for nested spans of competences. To improve upon coarse-grained annotations, we make use of The European Skills, Competences, Qualifications and Occupations (ESCO; le Vrang et al., 2014) taxonomy API to obtain fine-grained labels via distant supervision. We study two setups: The zero-shot and few-shot classification setting. We fine-tune English-based models and RemBERT (Chung et al., 2020) and compare them to in-language Danish models. Our results show RemBERT significantly outperforms all other models in both the zero-shot and the few-shot setting.
Authors: Filippo Chiarello, Gualtiero Fantoni, Terence Hogarth, Vito Giordano, Liga Baltina, and Irene Spadaa
Abstract: Evidence is presented here of how text-mining techniques can be applied to the analysis of data on emerging skill needs arising from Industry 4.0 to ensure that ESCO provides information which is current. The alignment between ESCO and Industry 4.0 technological trends is analysed. Using text mining techniques, information is extracted on Industry 4.0 technologies from: (i) two versions of ESCO (v1.0 - v1.1.); and (ii) from the 4.0 related scientific literature. These are then compared to identify potential data gaps in ESCO. The findings demonstrate that text mining applied on scientific literature to extract technology trends, can help policy makers to provide more up-to-date labour market intelligence.
Authors: Cath Sleeman (NESTA)
Abstract: The Observatory provides insights on the skills mentioned in UK job adverts. We began collecting online job postings in January 2021 and the Observatory now contains several million job adverts. This article provides an introduction to the Observatory, and the data visualisations show some of the data series that are available to download.
Authors: Lucía Gorjón, Sara de la Rica, Aitor Sedano (ISEAK)
Abstract: This study addresses the empirical relationship between job tasks and employment share changes in Spain for the period 1997-2019. To do so, we use the novel European representative data on skills/tasks ESCO. Overall, we find a need for requalification in the Spanish workforce. We show that changes in employment shares are heterogeneously distributed by task content – there is an overall decline in the demand for routine-manual skills, while technological and social interaction skills have emerged. [...]
Authors: Irene Arcelay, Aitor Goti, Aitor Oyarbide-Zubillaga, Tugce Akyazi, Elisabete Alberdi and Pablo Garcia-Bringas
Abstract: This article aims to determine the current skills of the renewable energy industry workforce and to predict the upcoming skill requirements linked to a digital transition by creating a unified database that contains both types of skills. This will serve as a tool for renewable energy businesses, education centers, and policymakers to plan the training itinerary necessary to close the skills gap, as part of the sectoral strategy to achieve a competent future workforce.
Abstract: The adoption of the European Skills, Competencies, Occupations and Qualifications (ESCO) framework will affect everyone engaged in employment and education within the European Union. Preparing for change and embracing the possibilities of a continent-wide shared ontology will enable your organization to better serve your clients. Learn more about the possibilities and challenges.
Authors: Tugce Akyazi, Aitor Goti, Aitor Oyarbide, Elisabete Alberdi and Felix Bayon
Abstract: In this work, we introduce an industry-driven proactive strategy to achieve a successful digital transformation in the food sector. For that purpose, we focus on defining the current and near-future key skills and competencies demanded by each of the professional profiles related to the food industry. To achieve this, we generated an automated database of current and future professions and competencies and skills. This database can be used as a fundamental roadmap guiding the sector through future changes caused by Industry 4.0. The interest shown by the local sectorial cluster and related entities reinforce the idea. This research will be a key tool for both academics and policy-makers to provide well-developed and better-oriented continuous training programs in order to reduce the skill mismatch between the workforce and the jobs.
Authors: Karlis Kanders, Jyldyz Djumalieva, Cath Sleeman, Jack Orlik (NESTA)
Abstract: To date, most automation research has focused on identifying which occupations are most at risk of automation. This report goes one step further, by providing guidance on how workers (in the UK, France and Italy) can transition out of these occupations and into lower-risk roles. This guidance is made possible by an algorithm that estimates the similarity between over 1,600 jobs, based on the skills and work experiences required in each role.
Author: World Economic Forum
Abstract: The proposed taxonomy builds on the recognized work taken forward by ESCO (European Skills, Competences and Occupations) and the Occupational Information Network (O*NET) framework by integrating additional emerging skills and attitudes, particularly as they relate to the trends highlighted in the Forum’s ongoing insights on the future of work. It aims to take a matrixed approach that combines skills and occupations.
Abstract: In response to the Covid-19 pandemic, professionals around the globe were forced to abruptly change the way they work and transition, to the extent possible, toward remote work arrangements. The results of this study conducted on over ten thousand skills and nearly three thousand jobs show that out of all technical skills, about half correspond
to tasks that can be done at least partly from home.
Abstract: This publication takes a task-based approach to studying the impact of automation on jobs and skills. By combining a comprehensive occupational dataset with task automation data, we define and compute an automation index between 0 and 100%, corresponding to the risk of automation for any job (or skill) given the current state of technology.
Abstract: The recruitment market is gradually shifting its focus from requiring knowledges to requiring skills. Soft skills, in particular, have become crucial for employers when it comes to assessing which candidates will best fit within a given team or within the larger company setting. The present study examines the link between soft skills and recruitment.
Author: Álvaro Altamirano and Nicole Amaral (Inter-American Development Bank)
Abstract: This note brings together lessons from the IDBs and other institutions efforts to adapt a skills taxonomy for Latin America and the Caribbean countries. These efforts have focused primarily on the ability to gather and make use of labor market information on skills demand from non-traditional data sources like online job vacancies. Most of these efforts have used the European Skills, Competences, Qualifications and Occupations (ESCO) taxonomy to underpin the identification and classification of skills. This note is intended to be a starting point and set of considerations for policymakers who may be considering, or already embarking on, similar efforts to use ESCO or other taxonomical structures to help better analyze, understand and use skills-level information for decision making. It also seeks to motivate the need for additional classification systems that help governments take stock of its citizens skills in increasingly complex and rapidly changing labor markets.
Authors: Pascaline Descy, Vladimir Kvetan, Albrecht Wirthmann, and Fernando Reis
Abstract: Following the increasing penetration of the internet, the number of websites that advertise jobs is growing. The European Centre for the Development of Vocational Training (Cedefop) and the ESSnet Big Data have engaged in parallel projects to assess the feasibility of using online job advertisements (OJA) for labour market analysis and job vacancy statistics. After an initial feasibility study finalised in 2016, Cedefop is developing a Pan-EU system providing information on skills demand present in OJA, which will be operational by 2020. [...]
Abstract: Despite the wealth of information available to job seekers, choosing careers and transitioning between jobs remain a complex endeavor. With millions of job titles available, it is difficult for candidates to know what each role entitles and how well-suited they are for various open positions. Our research aims to break through this complexity and provide a quantitative framework for recommending job transitions. We use a comprehensive job and skill data set with annotated variables (job activity, job seniority) in conjunction with a multivariate technique to create a matching score for any job pair (A, B). The multivariate combination relies on the similarity between the titles of jobs A and B, their descriptions, and their required skills. This model is used to determine the top 10 recommendations for each of the 3,190 jobs in the data set considered for this analysis.
Authors: CEDEFOP and OECD
Abstract: As the green transition creates new skill needs across sectors and occupations, implications for preparing, reskilling and upskilling the workforce emerge for vocational education and training. This publication draws from practices and research and provides insights into how apprenticeships can promote and react to a green economy and society, from small-scale modular curriculum adaptation, to more encompassing sectoral or regional approaches. In this way, apprenticeships demonstrate transformative potential for economies and societies, responding to the opportunities and challenges that may support a green recovery that leaves no one behind.
Lexical taxonomies are widely used to foster information retrieval and exchange in several domains and applications. When there are multiple taxonomies, heterogeneity among them is a severe problem for efficient collaboration processes. In this paper, we propose WETA, a domain-independent, knowledge-poor method for automatic taxonomy alignment via word embeddings. WETA associates all the leaf terms of the origin taxonomy to one or many concepts in the destination taxonomy, employing a scoring function, which merges the score of a hierarchical method based on cosine similarity and the score of a classification task. WETA is developed in the context of an EU Grant aiming at bridging the national taxonomies of EU countries towards the European Skills, Competences, Qualifications and Occupations taxonomy (ESCO) using AI Algorithms. The results, validated within the EU project activities for bridging the Italian occupation taxonomy CP and ESCO, confirm the usefulness of WETA in supporting the automatic alignment of national labor taxonomies. WETA reaches a 0.8 accuracy on recommending top-5 occupations and a wMRR of 0.72. WETA reduces the human effort needed for building a mapping from scratch: it would allow domain experts to concentrate on the validation task and decrease the incoherence due to multiple judgments. It would also make the approach reproducible and transparent to policymakers.