In the last decade, the fast technological and social transformations have been placing new demands on Higher Education (HE) systems to update their educational offers. Grounded in the broader discourse on the impact of such transformation on HE, this article relies on Text Mining (TM). We consider as a case study the Italian HE system, providing an overview of the university education in the last 10 Academic Years. We automatically analyse 54,535 learning outcomes of degree programmes to identify the relevant topics with Named Entity Recognition, a technique of TM. For each topic, we measured its trend in time and coverage on a geographical basis and in the disciplinary fields. We detected 6062 different topics, among these the most growing are artificial intelligence, sustainability, rare diseases, and ethics. The findings reveal that topics related to hard sciences register higher occurrence than the ones concerning humanities and social sciences. Furthermore, we observed that universities are overcoming the boundaries of disciplinary fields, promoting knowledge contamination and vertical specialisation. The proposed approach can advance studies in HE literature for effective and efficient analysis. The findings can inform policies and practices in HE on evolving learning outcomes and educational offerings, even across different countries and disciplines.

Tracing topic evolution in higher education: a text mining study on Italian universities

Irene Spada
;
Vito Giordano
Secondo
;
Filippo Chiarello;Gualtiero Fantoni
Ultimo
;
Marco Abate;Francesca Maria Dovetto
Penultimo
2023-01-01

Abstract

In the last decade, the fast technological and social transformations have been placing new demands on Higher Education (HE) systems to update their educational offers. Grounded in the broader discourse on the impact of such transformation on HE, this article relies on Text Mining (TM). We consider as a case study the Italian HE system, providing an overview of the university education in the last 10 Academic Years. We automatically analyse 54,535 learning outcomes of degree programmes to identify the relevant topics with Named Entity Recognition, a technique of TM. For each topic, we measured its trend in time and coverage on a geographical basis and in the disciplinary fields. We detected 6062 different topics, among these the most growing are artificial intelligence, sustainability, rare diseases, and ethics. The findings reveal that topics related to hard sciences register higher occurrence than the ones concerning humanities and social sciences. Furthermore, we observed that universities are overcoming the boundaries of disciplinary fields, promoting knowledge contamination and vertical specialisation. The proposed approach can advance studies in HE literature for effective and efficient analysis. The findings can inform policies and practices in HE on evolving learning outcomes and educational offerings, even across different countries and disciplines.
2023
Spada, Irene; Giordano, Vito; Chiarello, Filippo; Fantoni, Gualtiero; Abate, Marco; Dovetto, Francesca Maria
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11568/1215790
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
social impact