This paper presents a refinement of PrOnto ontology using a validation test based on legal experts’ annotation of privacy policies combined with an Open Knowledge Extraction (OKE) algorithm. To ensure robustness of the results while preserving an interdisciplinary approach, the integration of legal and technical knowledge has been carried out as follows. The set of privacy policies was first analysed by the legal experts to discover legal concepts and map the text into PrOnto. The mapping was then provided to computer scientists to perform the OKE analysis. Results were validated by the legal experts, who provided feedbacks and refinements (i.e. new classes and modules) of the ontology according to MeLOn methodology. Three iterations were performed on a set of (development) policies, and a final test using a new set of privacy policies. The results are 75,43% of detection of concepts in the policy texts and an increase of roughly 33% in the accuracy gain on the test set, using the new refined version of PrOnto enriched with SKOS-XL lexicon terms and definitions.

Palmirani, M., Bincoletto, G., Leone, V., Sapienza, S., Sovrano, F. (2020). Hybrid Refining Approach of PrOnto Ontology. Cham : Springer [10.1007/978-3-030-58957-8_1].

Hybrid Refining Approach of PrOnto Ontology

Palmirani, Monica
;
Bincoletto, Giorgia;Leone, Valentina;Sapienza, Salvatore;Sovrano, Francesco
2020

Abstract

This paper presents a refinement of PrOnto ontology using a validation test based on legal experts’ annotation of privacy policies combined with an Open Knowledge Extraction (OKE) algorithm. To ensure robustness of the results while preserving an interdisciplinary approach, the integration of legal and technical knowledge has been carried out as follows. The set of privacy policies was first analysed by the legal experts to discover legal concepts and map the text into PrOnto. The mapping was then provided to computer scientists to perform the OKE analysis. Results were validated by the legal experts, who provided feedbacks and refinements (i.e. new classes and modules) of the ontology according to MeLOn methodology. Three iterations were performed on a set of (development) policies, and a final test using a new set of privacy policies. The results are 75,43% of detection of concepts in the policy texts and an increase of roughly 33% in the accuracy gain on the test set, using the new refined version of PrOnto enriched with SKOS-XL lexicon terms and definitions.
2020
Electronic Government and the Information Systems Perspective.
3
17
Palmirani, M., Bincoletto, G., Leone, V., Sapienza, S., Sovrano, F. (2020). Hybrid Refining Approach of PrOnto Ontology. Cham : Springer [10.1007/978-3-030-58957-8_1].
Palmirani, Monica; Bincoletto, Giorgia; Leone, Valentina; Sapienza, Salvatore; Sovrano, Francesco
File in questo prodotto:
File Dimensione Formato  
502031_1_En_Print.indd.pdf

accesso riservato

Tipo: Versione (PDF) editoriale
Licenza: Licenza per accesso riservato
Dimensione 2.12 MB
Formato Adobe PDF
2.12 MB Adobe PDF   Visualizza/Apri   Contatta l'autore
post print Hybrid Refining Approach.pdf

Open Access dal 07/09/2021

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 1.31 MB
Formato Adobe PDF
1.31 MB Adobe PDF Visualizza/Apri

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/11585/773147
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 6
social impact