Car accident causes are relevant both for insurance companies as well as for policy makers. The former are interested into the dynamics of the accidents in order to evaluate responsibilities, the latter to foster good driving behavior for the sake of social benefit, too. By using a large set of medical and police reports, and by exploiting Natural Language Processing techniques we aim at grasping latent information useful to classify them according to the relevance of their content.

Cantaluppi, G., Zappa, D., Modelling Topics of Car Accidents Events: A Text Mining Approach, in Corazza, M., Gilli, M., Perna, C., Pizzi, C., Sibillo, M. (ed.), Mathematical and Statistical Methods for Actuarial Sciences and Finance, Springer, Cham 2021: 117- 122. 10.1007/978-3-030-78965-7_18 [http://hdl.handle.net/10807/191191]

Modelling Topics of Car Accidents Events: A Text Mining Approach

Cantaluppi, Gabriele
;
Zappa, Diego
2021

Abstract

Car accident causes are relevant both for insurance companies as well as for policy makers. The former are interested into the dynamics of the accidents in order to evaluate responsibilities, the latter to foster good driving behavior for the sake of social benefit, too. By using a large set of medical and police reports, and by exploiting Natural Language Processing techniques we aim at grasping latent information useful to classify them according to the relevance of their content.
Inglese
Mathematical and Statistical Methods for Actuarial Sciences and Finance
978-3-030-78964-0
Springer
Cantaluppi, G., Zappa, D., Modelling Topics of Car Accidents Events: A Text Mining Approach, in Corazza, M., Gilli, M., Perna, C., Pizzi, C., Sibillo, M. (ed.), Mathematical and Statistical Methods for Actuarial Sciences and Finance, Springer, Cham 2021: 117- 122. 10.1007/978-3-030-78965-7_18 [http://hdl.handle.net/10807/191191]
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: http://hdl.handle.net/10807/191191
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact