@inproceedings{volodina-etal-2020-towards,
title = "Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of {S}wedish Learner Essays",
author = "Volodina, Elena and
Ali Mohammed, Yousuf and
Derbring, Sandra and
Matsson, Arild and
Megyesi, Beata",
editor = "Scott, Donia and
Bel, Nuria and
Zong, Chengqing",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.32",
doi = "10.18653/v1/2020.coling-main.32",
pages = "357--369",
abstract = "This article reports on an ongoing project aiming at automatization of pseudonymization of learner essays. The process includes three steps: identification of personal information in an unstructured text, labeling for a category, and pseudonymization. We experiment with rule-based methods for detection of 15 categories out of the suggested 19 (Megyesi et al., 2018) that we deem important and/or doable with automatic approaches. For the detection and labeling steps,we use resources covering personal names, geographic names, company and university names and others. For the pseudonymization step, we replace the item using another item of the same type from the above-mentioned resources. Evaluation of the detection and labeling steps are made on a set of manually anonymized essays. The results are promising and show that 89{\%} of the personal information can be successfully identified in learner data, and annotated correctly with an inter-annotator agreement of 86{\%} measured as Fleiss kappa and Krippendorff{'}s alpha.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="volodina-etal-2020-towards">
<titleInfo>
<title>Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Volodina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yousuf</namePart>
<namePart type="family">Ali Mohammed</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Derbring</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arild</namePart>
<namePart type="family">Matsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Megyesi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Donia</namePart>
<namePart type="family">Scott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nuria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article reports on an ongoing project aiming at automatization of pseudonymization of learner essays. The process includes three steps: identification of personal information in an unstructured text, labeling for a category, and pseudonymization. We experiment with rule-based methods for detection of 15 categories out of the suggested 19 (Megyesi et al., 2018) that we deem important and/or doable with automatic approaches. For the detection and labeling steps,we use resources covering personal names, geographic names, company and university names and others. For the pseudonymization step, we replace the item using another item of the same type from the above-mentioned resources. Evaluation of the detection and labeling steps are made on a set of manually anonymized essays. The results are promising and show that 89% of the personal information can be successfully identified in learner data, and annotated correctly with an inter-annotator agreement of 86% measured as Fleiss kappa and Krippendorff’s alpha.</abstract>
<identifier type="citekey">volodina-etal-2020-towards</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.32</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.32</url>
</location>
<part>
<date>2020-12</date>
<extent unit="page">
<start>357</start>
<end>369</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays
%A Volodina, Elena
%A Ali Mohammed, Yousuf
%A Derbring, Sandra
%A Matsson, Arild
%A Megyesi, Beata
%Y Scott, Donia
%Y Bel, Nuria
%Y Zong, Chengqing
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 December
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F volodina-etal-2020-towards
%X This article reports on an ongoing project aiming at automatization of pseudonymization of learner essays. The process includes three steps: identification of personal information in an unstructured text, labeling for a category, and pseudonymization. We experiment with rule-based methods for detection of 15 categories out of the suggested 19 (Megyesi et al., 2018) that we deem important and/or doable with automatic approaches. For the detection and labeling steps,we use resources covering personal names, geographic names, company and university names and others. For the pseudonymization step, we replace the item using another item of the same type from the above-mentioned resources. Evaluation of the detection and labeling steps are made on a set of manually anonymized essays. The results are promising and show that 89% of the personal information can be successfully identified in learner data, and annotated correctly with an inter-annotator agreement of 86% measured as Fleiss kappa and Krippendorff’s alpha.
%R 10.18653/v1/2020.coling-main.32
%U https://aclanthology.org/2020.coling-main.32
%U https://doi.org/10.18653/v1/2020.coling-main.32
%P 357-369
Markdown (Informal)
[Towards Privacy by Design in Learner Corpora Research: A Case of On-the-fly Pseudonymization of Swedish Learner Essays](https://aclanthology.org/2020.coling-main.32) (Volodina et al., COLING 2020)
ACL