Towards Personal Data Anonymization for Social Messaging

D 2021

Towards Personal Data Anonymization for Social Messaging

SOTOLÁŘ, Ondřej, Jaromír PLHÁK a David ŠMAHEL

Základní údaje

Originální název

Towards Personal Data Anonymization for Social Messaging

Autoři

SOTOLÁŘ, Ondřej (203 Česká republika, garant, domácí), Jaromír PLHÁK (203 Česká republika, domácí) a David ŠMAHEL (203 Česká republika, domácí)

Vydání

Cham, Text, Speech, and Dialogue, od s. 281-292, 12 s. 2021

Nakladatel

Springer, Cham

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

URL

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/21:00119196

Organizační jednotka

Fakulta informatiky

ISBN

978-3-030-83526-2

ISSN

DOI

http://dx.doi.org/10.1007/978-3-030-83527-9_24

Klíčová slova anglicky

Text anonymization; Personal data; Sanitization; De-identification; Privacy protection

Štítky

firank_B

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 9. 9. 2021 13:23, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

We present a method for building text corpora for the supervised learning of text-to-text anonymization while maintaining a strict privacy policy. In our solution, personal data entities are detected, classified, and anonymized. We use available machine-learning methods, like named-entity recognition, and improve their performance by grouping multiple entities into larger units based on the theory of tabular data anonymization. Experimental results on annotated Czech Facebook Messenger conversations reveal that our solution has recall comparable to human annotators. On the other hand, precision is much lower because of the low efficiency of the named entity recognition in the domain of social messaging conversations. The resulting anonymized text is of high utility because of the replacement methods that produce natural text.

Návaznosti

GX19-27828X, projekt VaV

Název: Pohled do budoucnosti: Porozumění vlivu technologií na “well-being” adolescentů (Akronym: FUTURE)

Investor: Grantová agentura ČR, Modelling the future: Understanding the impact of technology on adolescent’s well-being

Citovat

SOTOLÁŘ, Ondřej, Jaromír PLHÁK a David ŠMAHEL. Towards Personal Data Anonymization for Social Messaging. In Kamil Ekštein, František Pártl, Miloslav Konopík. Text, Speech, and Dialogue. Cham: Springer, Cham, 2021, s. 281-292. ISBN 978-3-030-83526-2. Dostupné z: https://dx.doi.org/10.1007/978-3-030-83527-9_24.

@inproceedings{1790654,
   author = {Sotolář, Ondřej and Plhák, Jaromír and Šmahel, David},
   address = {Cham},
   booktitle = {Text, Speech, and Dialogue},
   doi = {http://dx.doi.org/10.1007/978-3-030-83527-9_24},
   editor = {Kamil Ekštein, František Pártl, Miloslav Konopík},
   keywords = {Text anonymization; Personal data; Sanitization; De-identification; Privacy protection},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Cham},
   isbn = {978-3-030-83526-2},
   pages = {281-292},
   publisher = {Springer, Cham},
   title = {Towards Personal Data Anonymization for Social Messaging},
   url = {https://link.springer.com/chapter/10.1007/978-3-030-83527-9_24},
   year = {2021}
}

TY  - JOUR
ID  - 1790654
AU  - Sotolář, Ondřej - Plhák, Jaromír - Šmahel, David
PY  - 2021
TI  - Towards Personal Data Anonymization for Social Messaging
PB  - Springer, Cham
CY  - Cham
SN  - 9783030835262
KW  - Text anonymization
KW  - Personal data
KW  - Sanitization
KW  - De-identification
KW  - Privacy protection
UR  - https://link.springer.com/chapter/10.1007/978-3-030-83527-9_24
N2  - We present a method for building text corpora for the supervised learning of text-to-text anonymization while maintaining a strict privacy policy. In our solution, personal data entities are detected, classified, and anonymized. We use available machine-learning methods, like named-entity recognition, and improve their performance by grouping multiple entities into larger units based on the theory of tabular data anonymization. Experimental results on annotated Czech Facebook Messenger conversations reveal that our solution has recall comparable to human annotators. On the other hand, precision is much lower because of the low efficiency of the named entity recognition in the domain of social messaging conversations. The resulting anonymized text is of high utility because of the replacement methods that produce natural text.
ER  -

SOTOLÁŘ, Ondřej, Jaromír PLHÁK a David ŠMAHEL. Towards Personal Data Anonymization for Social Messaging. In Kamil Ekštein, František Pártl, Miloslav Konopík. \textit{Text, Speech, and Dialogue}. Cham: Springer, Cham, 2021, s.~281-292. ISBN~978-3-030-83526-2. Dostupné z: https://dx.doi.org/10.1007/978-3-030-83527-9\_{}24.

Podrobný výpis o publikaci