@inproceedings{knockel-etal-2018-effect,
title = "The effect of information controls on developers in {C}hina: An analysis of censorship in {C}hinese open source projects",
author = "Knockel, Jeffrey and
Crete-Nishihata, Masashi and
Ruan, Lotus",
editor = "Brew, Chris and
Feldman, Anna and
Leberknight, Chris",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for {I}nternet Freedom",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4201",
pages = "1--11",
abstract = "Censorship of Internet content in China is understood to operate through a system of intermediary liability whereby service providers are liable for the content on their platforms. Previous work studying censorship has found huge variability in the implementation of censorship across different products even within the same industry segment. In this work we explore the extent to which these censorship features are present in the open source projects of individual developers in China by collecting their blacklists and comparing their similarity. We collect files from a popular online code repository, extract lists of strings, and then classify whether each is a Chinese blacklist. Overall, we found over 1,000 Chinese blacklists comprising over 200,000 unique keywords, representing the largest dataset of Chinese blacklisted keywords to date. We found very little keyword overlap between lists, raising questions as to their origins, as the lists seem too large to have been individually curated, yet the lack of overlap suggests that they have no common source.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="knockel-etal-2018-effect">
<titleInfo>
<title>The effect of information controls on developers in China: An analysis of censorship in Chinese open source projects</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Knockel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masashi</namePart>
<namePart type="family">Crete-Nishihata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lotus</namePart>
<namePart type="family">Ruan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Internet Freedom</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Brew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Censorship of Internet content in China is understood to operate through a system of intermediary liability whereby service providers are liable for the content on their platforms. Previous work studying censorship has found huge variability in the implementation of censorship across different products even within the same industry segment. In this work we explore the extent to which these censorship features are present in the open source projects of individual developers in China by collecting their blacklists and comparing their similarity. We collect files from a popular online code repository, extract lists of strings, and then classify whether each is a Chinese blacklist. Overall, we found over 1,000 Chinese blacklists comprising over 200,000 unique keywords, representing the largest dataset of Chinese blacklisted keywords to date. We found very little keyword overlap between lists, raising questions as to their origins, as the lists seem too large to have been individually curated, yet the lack of overlap suggests that they have no common source.</abstract>
<identifier type="citekey">knockel-etal-2018-effect</identifier>
<location>
<url>https://aclanthology.org/W18-4201</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>1</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The effect of information controls on developers in China: An analysis of censorship in Chinese open source projects
%A Knockel, Jeffrey
%A Crete-Nishihata, Masashi
%A Ruan, Lotus
%Y Brew, Chris
%Y Feldman, Anna
%Y Leberknight, Chris
%S Proceedings of the First Workshop on Natural Language Processing for Internet Freedom
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F knockel-etal-2018-effect
%X Censorship of Internet content in China is understood to operate through a system of intermediary liability whereby service providers are liable for the content on their platforms. Previous work studying censorship has found huge variability in the implementation of censorship across different products even within the same industry segment. In this work we explore the extent to which these censorship features are present in the open source projects of individual developers in China by collecting their blacklists and comparing their similarity. We collect files from a popular online code repository, extract lists of strings, and then classify whether each is a Chinese blacklist. Overall, we found over 1,000 Chinese blacklists comprising over 200,000 unique keywords, representing the largest dataset of Chinese blacklisted keywords to date. We found very little keyword overlap between lists, raising questions as to their origins, as the lists seem too large to have been individually curated, yet the lack of overlap suggests that they have no common source.
%U https://aclanthology.org/W18-4201
%P 1-11
Markdown (Informal)
[The effect of information controls on developers in China: An analysis of censorship in Chinese open source projects](https://aclanthology.org/W18-4201) (Knockel et al., NLP4IF 2018)
ACL