Crime alert! crime typification in news based on text mining

Hugo Alatrista-Salas; Juandiego Morzán-Samamé; Miguel Nunez-del-Prado

doi:10.1007/978-3-030-12388-8_50

Crime alert! crime typification in news based on text mining

Hugo Alatrista-Salas, Juandiego Morzán-Samamé, Miguel Nunez-del-Prado

Universidad del Pacífico

Producción científica: Capítulo del libro/informe/acta de congreso › Capítulo › revisión exhaustiva

7 Citas (Scopus)

Resumen

In this paper we detailed a multinomial classification-based methodology that combines different algorithms (SVM and MLP) with document representations (Tf Idf vectorization and Doc2vec embedding) and: (i) can distinguish between crime-related news and not-crime related news and; (ii) allows the assignment of each crime-related news to its corresponding crime type. With a F1-score of 84% achieved by the MLP with Doc2vec approach, it can be concluded that it is possible to answer the question of how the crimes are committed (what types of crime are perpetrated) and, in this way, offer a thermometer to citizens about criminal activity in a given territory, as reported by news articles.

Idioma original	Inglés
Título de la publicación alojada	Lecture Notes in Networks and Systems
Editorial	Springer
Páginas	725-741
Número de páginas	17
DOI	https://doi.org/10.1007/978-3-030-12388-8_50
Estado	Publicada - 2020
Publicado de forma externa	Sí

Serie de la publicación

Nombre	Lecture Notes in Networks and Systems
Volumen	69
ISSN (versión impresa)	2367-3370
ISSN (versión digital)	2367-3389

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

Acceder al documento

10.1007/978-3-030-12388-8_50

Otros archivos y enlaces

Enlace a la publicación en Scopus

Citar esto

@inbook{778d2ffc158f477cb7f68d7c8902a129,

title = "Crime alert! crime typification in news based on text mining",

abstract = "In this paper we detailed a multinomial classification-based methodology that combines different algorithms (SVM and MLP) with document representations (Tf Idf vectorization and Doc2vec embedding) and: (i) can distinguish between crime-related news and not-crime related news and; (ii) allows the assignment of each crime-related news to its corresponding crime type. With a F1-score of 84% achieved by the MLP with Doc2vec approach, it can be concluded that it is possible to answer the question of how the crimes are committed (what types of crime are perpetrated) and, in this way, offer a thermometer to citizens about criminal activity in a given territory, as reported by news articles.",

keywords = "Classification, Crime analysis, Text mining, Word vectorization and embeddings",

author = "Hugo Alatrista-Salas and Juandiego Morz{\'a}n-Samam{\'e} and Miguel Nunez-del-Prado",

note = "Publisher Copyright: {\textcopyright} Springer Nature Switzerland AG 2020.",

year = "2020",

doi = "10.1007/978-3-030-12388-8_50",

language = "English",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "725--741",

booktitle = "Lecture Notes in Networks and Systems",

}

TY - CHAP

T1 - Crime alert! crime typification in news based on text mining

AU - Alatrista-Salas, Hugo

AU - Morzán-Samamé, Juandiego

AU - Nunez-del-Prado, Miguel

N1 - Publisher Copyright: © Springer Nature Switzerland AG 2020.

PY - 2020

Y1 - 2020

N2 - In this paper we detailed a multinomial classification-based methodology that combines different algorithms (SVM and MLP) with document representations (Tf Idf vectorization and Doc2vec embedding) and: (i) can distinguish between crime-related news and not-crime related news and; (ii) allows the assignment of each crime-related news to its corresponding crime type. With a F1-score of 84% achieved by the MLP with Doc2vec approach, it can be concluded that it is possible to answer the question of how the crimes are committed (what types of crime are perpetrated) and, in this way, offer a thermometer to citizens about criminal activity in a given territory, as reported by news articles.

AB - In this paper we detailed a multinomial classification-based methodology that combines different algorithms (SVM and MLP) with document representations (Tf Idf vectorization and Doc2vec embedding) and: (i) can distinguish between crime-related news and not-crime related news and; (ii) allows the assignment of each crime-related news to its corresponding crime type. With a F1-score of 84% achieved by the MLP with Doc2vec approach, it can be concluded that it is possible to answer the question of how the crimes are committed (what types of crime are perpetrated) and, in this way, offer a thermometer to citizens about criminal activity in a given territory, as reported by news articles.

KW - Classification

KW - Crime analysis

KW - Text mining

KW - Word vectorization and embeddings

UR - http://www.scopus.com/inward/record.url?scp=85062905236&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-12388-8_50

DO - 10.1007/978-3-030-12388-8_50

M3 - Chapter

AN - SCOPUS:85062905236

T3 - Lecture Notes in Networks and Systems

SP - 725

EP - 741

BT - Lecture Notes in Networks and Systems

PB - Springer

ER -

Crime alert! crime typification in news based on text mining

Resumen

Serie de la publicación

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto