The global transformation led by the Fourth Industrial Revolution, the environmental changes, and the Covid-19 pandemic, calls for new social and economic growth models. Critical actions are required in industries and societies to ensure sustainable development, as established in several programs. The International Agenda 2030 revolves around 5 key pillars (planet, people, prosperity, global peace, partnership) and 17 Sustainable Development Goals. The European Green Deal aims at transforming the European Union (EU) into a modern, resource-efficient and competitive economy. To support green transition, in 2020, the European Commision developed the EU Taxonomy for Sustainable Activities (hereinafter, EU-TSA or Taxonomy), explaining industrial activities’ contribution towards sustainable economics. Beside political actions, industrial stakeholders should rethink the entire supply chains, focusing on the vulnerability of the environment and the effects of human activities on it [1]. Moving to the labour market, policies and regulations are changing needs and requirements in employment. Companies are pushed to seek green workers with key-enabling capabilities, related both to activities and mindset orientation for sustainability [2]. Actually the European Classification of Skills/Competences, Qualifications and Occupations (ESCO) has been just updated with green concepts to properly support labour market and education in the transition. Several studies in literature attempt to delineate the green worker and in general the concepts related to sustainable development since the ‘90s [3]. Some authors propose surveys to identify a definition of green skills and jobs [4, 5]. Others leverage text mining techniques to discover the embedded information in job descriptions [6]. Indeed, the fast pace of twin transition requires the most up-to-date data to understand emerging labour force characteristics. However, the complexity of such phenomena demands for trusted and integrated data-sources to connect information and have a broad comprehension from multiple perspectives. This is why we aim to detect links and gaps between tasks and skills of green workers by contrasting and comparing two European policies recently released. Such an approach may help in identifying key-enabling competencies for green-related activities. We measured the alignment between the EU-TSA and green concepts of ESCO using Natural Language Processing (NLP) techniques. The former includes 183 activities with labels, descriptions, and connections to six environmental objectives. The latter consists of 570 skills and knowledge. We developed a list of green-related expressions from the EU-TSA, by tokenizing the text of labels and descriptions, i.e., splitting sentences into a stream of words. Then, we filtered the relevant expressions using cleaning-rules, frequency analysis and revision. Finally, we applied string-matching algorithms to identify the green-related expressions in the ESCO skills. The list of green-related expressions from the EU-TSA encompasses above 700 terms, of which 110 are identified in the ESCO green skills classification. We found 95% of EU-TSA tasks connected to ESCO green skills and 87% ESCO green competences linked to sustainable activities of the Taxonomy. These results suggest a general alignment between the two sources. The matches can indicate which skills and knowledge contribute to the realisation of the related tasks, so how workers can handle daily activities in a sustainable manner. As an example, the task “electricity generation using solar photovoltaic technology” in EU-TSA (i.e., use renewable energies considering components’ durability and recyclability) is connected to technical skills such as “solar energy” and “coordinate electricity generation”, and transversal green approaches like “conduct energy audit” and “develop energy saving concepts”. Some green activities are not covered by the skills classification, such as the ones related to education, media management, and computer programming, probably because of the broad definition of these tasks in the Taxonomy. For example, media management should be related to some ESCO skills such as “advise on utility consumption” and “promote sustainability” to ensure green awareness and avoid greenwashing practices; however the task’s description refers only to the production of media contents. Vice-versa some green skills are not linked to green activities, maybe for the high specificity of those competences. For instance, the knowledge of pollution, pesticide and oil rig legislations should be pervasive in many of EU-TSA tasks, however these detailed regulations indicated in ESCO have no matches in the Taxonomy. In-depth analysis on misalignments can reveal which are the potential shortcomings to address in the green transition of the labour market. From an academic perspective, we compare and bridge two policy-related data (i.e., EU-TSA and ESCO), paving the way for new experiments aimed at analysing different policies in emerging scenarios (such as green, sustainability, Artificial Intelligence). Our first attempt to identify green-related terms with NLP could help researchers in exploring the impact of green transition. Our results can benefit practitioners of European institutions and companies in using the analysed frameworks. The identified gaps offer insights to increase the quality of the two policies. The mapped links boost their synergies: policy makers may better address the complexity of green transition; firms may use the bridge in guidelines' implementation. Finally, the proposed NLP approach could be used by Human Resource managers to gather key professionals-related information to face re/up-skilling green strategies. [1] Walker, A. M., Opferkuch, K., Lindgreen, E. R., Simboli, A., Vermeulen, W. J., & Raggi, A. (2021). Assessing the social sustainability of circular economy practices: Industry perspectives from Italy and the Netherlands. Sustainable Production and Consumption, 27, 831-844. [2] Consoli, D., Marin, G., Marzucchi, A., & Vona, F. (2016). Do green jobs differ from non-green jobs in terms of skills and human capital?. Research Policy, 45(5), 1046-1060. [3] Campbell, S. (1996). Green cities, growing cities, just cities?: Urban planning and the contradictions of sustainable development. Journal of the American Planning Association, 62(3), 296-312. [4] Bassi, F., & Guidolin, M. (2021). Resource efficiency and Circular Economy in European SMEs: Investigating the role of green jobs and skills. Sustainability, 13(21), 12136. [5] Nikolajenko-Skarbalė, J., Viederytė, R., & Šneiderienė, A. (2021). The Significance of “Green” Skills and Competencies Making the Transition Towards the “Greener” Economy. Rural Sustainability Research, 46(341), 53-65. [6] Fodor, S., Szabó, I., & Ternai, K. (2021). Competence-Oriented, Data-Driven Approach for Sustainable Development in University-Level Education. Sustainability, 13(17), 9977.
Discover Links and Gaps of Green Policies using Natural Language Processing
Irene Spada;Vito Giordano;Anastasia Dotolo;Gualtiero Fantoni
2022-01-01
Abstract
The global transformation led by the Fourth Industrial Revolution, the environmental changes, and the Covid-19 pandemic, calls for new social and economic growth models. Critical actions are required in industries and societies to ensure sustainable development, as established in several programs. The International Agenda 2030 revolves around 5 key pillars (planet, people, prosperity, global peace, partnership) and 17 Sustainable Development Goals. The European Green Deal aims at transforming the European Union (EU) into a modern, resource-efficient and competitive economy. To support green transition, in 2020, the European Commision developed the EU Taxonomy for Sustainable Activities (hereinafter, EU-TSA or Taxonomy), explaining industrial activities’ contribution towards sustainable economics. Beside political actions, industrial stakeholders should rethink the entire supply chains, focusing on the vulnerability of the environment and the effects of human activities on it [1]. Moving to the labour market, policies and regulations are changing needs and requirements in employment. Companies are pushed to seek green workers with key-enabling capabilities, related both to activities and mindset orientation for sustainability [2]. Actually the European Classification of Skills/Competences, Qualifications and Occupations (ESCO) has been just updated with green concepts to properly support labour market and education in the transition. Several studies in literature attempt to delineate the green worker and in general the concepts related to sustainable development since the ‘90s [3]. Some authors propose surveys to identify a definition of green skills and jobs [4, 5]. Others leverage text mining techniques to discover the embedded information in job descriptions [6]. Indeed, the fast pace of twin transition requires the most up-to-date data to understand emerging labour force characteristics. However, the complexity of such phenomena demands for trusted and integrated data-sources to connect information and have a broad comprehension from multiple perspectives. This is why we aim to detect links and gaps between tasks and skills of green workers by contrasting and comparing two European policies recently released. Such an approach may help in identifying key-enabling competencies for green-related activities. We measured the alignment between the EU-TSA and green concepts of ESCO using Natural Language Processing (NLP) techniques. The former includes 183 activities with labels, descriptions, and connections to six environmental objectives. The latter consists of 570 skills and knowledge. We developed a list of green-related expressions from the EU-TSA, by tokenizing the text of labels and descriptions, i.e., splitting sentences into a stream of words. Then, we filtered the relevant expressions using cleaning-rules, frequency analysis and revision. Finally, we applied string-matching algorithms to identify the green-related expressions in the ESCO skills. The list of green-related expressions from the EU-TSA encompasses above 700 terms, of which 110 are identified in the ESCO green skills classification. We found 95% of EU-TSA tasks connected to ESCO green skills and 87% ESCO green competences linked to sustainable activities of the Taxonomy. These results suggest a general alignment between the two sources. The matches can indicate which skills and knowledge contribute to the realisation of the related tasks, so how workers can handle daily activities in a sustainable manner. As an example, the task “electricity generation using solar photovoltaic technology” in EU-TSA (i.e., use renewable energies considering components’ durability and recyclability) is connected to technical skills such as “solar energy” and “coordinate electricity generation”, and transversal green approaches like “conduct energy audit” and “develop energy saving concepts”. Some green activities are not covered by the skills classification, such as the ones related to education, media management, and computer programming, probably because of the broad definition of these tasks in the Taxonomy. For example, media management should be related to some ESCO skills such as “advise on utility consumption” and “promote sustainability” to ensure green awareness and avoid greenwashing practices; however the task’s description refers only to the production of media contents. Vice-versa some green skills are not linked to green activities, maybe for the high specificity of those competences. For instance, the knowledge of pollution, pesticide and oil rig legislations should be pervasive in many of EU-TSA tasks, however these detailed regulations indicated in ESCO have no matches in the Taxonomy. In-depth analysis on misalignments can reveal which are the potential shortcomings to address in the green transition of the labour market. From an academic perspective, we compare and bridge two policy-related data (i.e., EU-TSA and ESCO), paving the way for new experiments aimed at analysing different policies in emerging scenarios (such as green, sustainability, Artificial Intelligence). Our first attempt to identify green-related terms with NLP could help researchers in exploring the impact of green transition. Our results can benefit practitioners of European institutions and companies in using the analysed frameworks. The identified gaps offer insights to increase the quality of the two policies. The mapped links boost their synergies: policy makers may better address the complexity of green transition; firms may use the bridge in guidelines' implementation. Finally, the proposed NLP approach could be used by Human Resource managers to gather key professionals-related information to face re/up-skilling green strategies. [1] Walker, A. M., Opferkuch, K., Lindgreen, E. R., Simboli, A., Vermeulen, W. J., & Raggi, A. (2021). Assessing the social sustainability of circular economy practices: Industry perspectives from Italy and the Netherlands. Sustainable Production and Consumption, 27, 831-844. [2] Consoli, D., Marin, G., Marzucchi, A., & Vona, F. (2016). Do green jobs differ from non-green jobs in terms of skills and human capital?. Research Policy, 45(5), 1046-1060. [3] Campbell, S. (1996). Green cities, growing cities, just cities?: Urban planning and the contradictions of sustainable development. Journal of the American Planning Association, 62(3), 296-312. [4] Bassi, F., & Guidolin, M. (2021). Resource efficiency and Circular Economy in European SMEs: Investigating the role of green jobs and skills. Sustainability, 13(21), 12136. [5] Nikolajenko-Skarbalė, J., Viederytė, R., & Šneiderienė, A. (2021). The Significance of “Green” Skills and Competencies Making the Transition Towards the “Greener” Economy. Rural Sustainability Research, 46(341), 53-65. [6] Fodor, S., Szabó, I., & Ternai, K. (2021). Competence-Oriented, Data-Driven Approach for Sustainable Development in University-Level Education. Sustainability, 13(17), 9977.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
