Privacy preserving text representation learning

Ghazaleh Beigi; Kai Shu; Ruocheng Guo; Suhang Wang; Huan Liu

doi:10.1145/3342220.3344925

Privacy preserving text representation learning

Ghazaleh Beigi, Kai Shu, Ruocheng Guo, Suhang Wang, Huan Liu

Computing and Augmented Intelligence, School of (IAFSE-SCAI)

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

25 Scopus citations

Abstract

Online users generate tremendous amounts of textual information by participating in different online activities. This data provides opportunities for researchers and business partners to understand individuals. However, this user-generated textual data not only can reveal the identity of the user but also may contain individual's private attribute information. Publishing the textual data thus compromises the privacy of users. It is challenging to design effective anonymization techniques for textual information which minimize the chances of re-identification and does not contain private information while retaining the textual semantic meaning. In this paper, we study this problem and propose a novel double privacy preserving text representation learning framework, DPText. We show the effectiveness of DPText in preserving privacy and utility.

Original language	English (US)
Title of host publication	HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media
Publisher	Association for Computing Machinery, Inc
Pages	275-276
Number of pages	2
ISBN (Electronic)	9781450368858
DOIs	https://doi.org/10.1145/3342220.3344925
State	Published - Sep 12 2019
Event	30th ACM Conference on Hypertext and Social Media, HT 2019 - Hof, Germany Duration: Sep 17 2019 → Sep 20 2019

Publication series

Name	HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media

Conference

Conference	30th ACM Conference on Hypertext and Social Media, HT 2019
Country/Territory	Germany
City	Hof
Period	9/17/19 → 9/20/19

ASJC Scopus subject areas

Software
Artificial Intelligence
Human-Computer Interaction
Computer Graphics and Computer-Aided Design

Access to Document

10.1145/3342220.3344925

Cite this

Privacy preserving text representation learning. / Beigi, Ghazaleh; Shu, Kai; Guo, Ruocheng et al.
HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media. Association for Computing Machinery, Inc, 2019. p. 275-276 (HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media).

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

Beigi, G, Shu, K, Guo, R, Wang, S & Liu, H 2019, Privacy preserving text representation learning. in HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media. HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media, Association for Computing Machinery, Inc, pp. 275-276, 30th ACM Conference on Hypertext and Social Media, HT 2019, Hof, Germany, 9/17/19. https://doi.org/10.1145/3342220.3344925

@inproceedings{c4f62de6bb1b4661a85200bfff3cdcb8,

title = "Privacy preserving text representation learning",

abstract = "Online users generate tremendous amounts of textual information by participating in different online activities. This data provides opportunities for researchers and business partners to understand individuals. However, this user-generated textual data not only can reveal the identity of the user but also may contain individual's private attribute information. Publishing the textual data thus compromises the privacy of users. It is challenging to design effective anonymization techniques for textual information which minimize the chances of re-identification and does not contain private information while retaining the textual semantic meaning. In this paper, we study this problem and propose a novel double privacy preserving text representation learning framework, DPText. We show the effectiveness of DPText in preserving privacy and utility.",

author = "Ghazaleh Beigi and Kai Shu and Ruocheng Guo and Suhang Wang and Huan Liu",

note = "Funding Information: This material is based upon the work supported, in part, by NSF #1614576, ARO W911NF-15-1-0328 and ONR N00014-17-1-2605. Publisher Copyright: {\textcopyright} 2019 Copyright held by the owner/author(s).; 30th ACM Conference on Hypertext and Social Media, HT 2019 ; Conference date: 17-09-2019 Through 20-09-2019",

year = "2019",

month = sep,

day = "12",

doi = "10.1145/3342220.3344925",

language = "English (US)",

series = "HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media",

publisher = "Association for Computing Machinery, Inc",

pages = "275--276",

booktitle = "HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media",

}

TY - GEN

T1 - Privacy preserving text representation learning

AU - Beigi, Ghazaleh

AU - Shu, Kai

AU - Guo, Ruocheng

AU - Wang, Suhang

AU - Liu, Huan

N1 - Funding Information: This material is based upon the work supported, in part, by NSF #1614576, ARO W911NF-15-1-0328 and ONR N00014-17-1-2605. Publisher Copyright: © 2019 Copyright held by the owner/author(s).

PY - 2019/9/12

Y1 - 2019/9/12

N2 - Online users generate tremendous amounts of textual information by participating in different online activities. This data provides opportunities for researchers and business partners to understand individuals. However, this user-generated textual data not only can reveal the identity of the user but also may contain individual's private attribute information. Publishing the textual data thus compromises the privacy of users. It is challenging to design effective anonymization techniques for textual information which minimize the chances of re-identification and does not contain private information while retaining the textual semantic meaning. In this paper, we study this problem and propose a novel double privacy preserving text representation learning framework, DPText. We show the effectiveness of DPText in preserving privacy and utility.

AB - Online users generate tremendous amounts of textual information by participating in different online activities. This data provides opportunities for researchers and business partners to understand individuals. However, this user-generated textual data not only can reveal the identity of the user but also may contain individual's private attribute information. Publishing the textual data thus compromises the privacy of users. It is challenging to design effective anonymization techniques for textual information which minimize the chances of re-identification and does not contain private information while retaining the textual semantic meaning. In this paper, we study this problem and propose a novel double privacy preserving text representation learning framework, DPText. We show the effectiveness of DPText in preserving privacy and utility.

UR - http://www.scopus.com/inward/record.url?scp=85073374620&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073374620&partnerID=8YFLogxK

U2 - 10.1145/3342220.3344925

DO - 10.1145/3342220.3344925

M3 - Conference contribution

T3 - HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media

SP - 275

EP - 276

BT - HT 2019 - Proceedings of the 30th ACM Conference on Hypertext and Social Media

PB - Association for Computing Machinery, Inc

T2 - 30th ACM Conference on Hypertext and Social Media, HT 2019

Y2 - 17 September 2019 through 20 September 2019

ER -

Privacy preserving text representation learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this