Modelling Topics of Car Accidents Events: A Text Mining Approach

Gabriele Cantaluppi; Diego Zappa

doi:10.1007/978-3-030-78965-7_18

Modelling Topics of Car Accidents Events: A Text Mining Approach

Gabriele Cantaluppi^*
, Diego Zappa

^*Corresponding author

Research output: Chapter in Book/Report/Conference proceeding › Chapter

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.

Original language	English
Title of host publication	Mathematical and Statistical Methods for Actuarial Sciences and Finance
Editors	M Corazza, M Gilli, C Perna, C Pizzi, M Sibillo
Pages	117-122
Number of pages	6
DOIs	https://doi.org/10.1007/978-3-030-78965-7_18
Publication status	Published - 2021

Keywords

Natural language processing
Policy premiums
Text mining

Access to Document

10.1007/978-3-030-78965-7_18

Cite this

@inbook{c391ed3929c94c84a17630a93d932438,

title = "Modelling Topics of Car Accidents Events: A Text Mining Approach",

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.",

keywords = "Natural language processing, Policy premiums, Text mining, Natural language processing, Policy premiums, Text mining",

author = "Gabriele Cantaluppi and Diego Zappa",

year = "2021",

doi = "10.1007/978-3-030-78965-7\_18",

language = "English",

isbn = "978-3-030-78964-0",

pages = "117--122",

editor = "M Corazza and M Gilli and C Perna and C Pizzi and M Sibillo",

booktitle = "Mathematical and Statistical Methods for Actuarial Sciences and Finance",

}

TY - CHAP

T1 - Modelling Topics of Car Accidents Events: A Text Mining Approach

AU - Cantaluppi, Gabriele

AU - Zappa, Diego

PY - 2021

Y1 - 2021

N2 - 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.

AB - 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.

KW - Natural language processing

KW - Policy premiums

KW - Text mining

KW - Natural language processing

KW - Policy premiums

KW - Text mining

UR - http://hdl.handle.net/10807/191191

U2 - 10.1007/978-3-030-78965-7_18

DO - 10.1007/978-3-030-78965-7_18

M3 - Chapter

SN - 978-3-030-78964-0

SP - 117

EP - 122

BT - Mathematical and Statistical Methods for Actuarial Sciences and Finance

A2 - Corazza, M

A2 - Gilli, M

A2 - Perna, C

A2 - Pizzi, C

A2 - Sibillo, M

ER -

Modelling Topics of Car Accidents Events: A Text Mining Approach

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this