Exportar Publicação

Lopes, A. L., Roseta-Palma, C. & Simaens, A. (2023). A machine learning approach for a CRIS research outputs' SDG classifications. euroCRIS Strategic Membership Meeting.

A. L. Lopes et al.,  "A machine learning approach for a CRIS research outputs' SDG classifications", in euroCRIS Strategic Membership Meeting, Pamplona, 2023

@misc{lopes2023_1732196577624,
	author = "Lopes, A. L. and Roseta-Palma, C. and Simaens, A.",
	title = "A machine learning approach for a CRIS research outputs' SDG classifications",
	year = "2023",
	howpublished = "Digital",
	url = "https://meeting.eurocris.org"
}

TY  - CPAPER
TI  - A machine learning approach for a CRIS research outputs' SDG classifications
T2  - euroCRIS Strategic Membership Meeting
AU  - Lopes, A. L.
AU  - Roseta-Palma, C.
AU  - Simaens, A.
PY  - 2023
CY  - Pamplona
UR  - https://meeting.eurocris.org
AB  - The Sustainable Development Goals (SDGs) were defined by the United Nations in 2015 to provide goalposts for humanity’s ambition to move towards a better planet, a prosperous economy, and an inclusive society by 2030. We stand roughly at the midpoint of the SDG implementation period, a good moment to take stock of developments. Higher education institutions (HEIs) play a fundamental role in the creation of knowledge and its dissemination, so they are crucial levers to ensure that the SDGs reach a wider audience. 
Accordingly, various studies have summarized the contributions of HEIs to the various SDGs in terms of their strategy (Leal Filho et al., 2023), education (Leal Filho et al., 2019), sustainability reporting in the sector (De la Poza et al., 2021) and, especially, research (Agnew et al., 2020). Many individual HEIs have committed to Agenda 2030 and wish to assess their own contributions to the SDG, yet not all have the resources to apply such methodologies themselves: many lack an adequate database of publications with SDG relevance, since manual assessments are time-consuming and might not reflect widely accepted categories.
Machine-learning (ML) can be a valuable tool in this task of automatically classifying scientific publications as to their contribution to the SDGs (Angin et al., 2022; Morales-Hernández et al., 2022), allowing HEIs to monitor their own contributions and appraise their impact as well as improving communication and increasing the engagement of the academic community. Current Research Information Systems (CRIS) are ideal candidates for deploying this kind of approach because they can combine the availability of research outputs and external communication features with internal machine-learning models to help researchers choose the most accurate SDGs for which their research output contributes to.
This presentation takes stock of the methodologies that have been applied to the assessment of research outputs as they relate to the SDGs, in our Institution’s CRIS, Ciência IUL . In particular, we focus on the machine-learning-based approach that was employed in the CRIS to help researchers choose the right SDGs to be associated with their research outputs (including publications and projects).
ER  -