@inproceedings{ng-etal-2019-neural,
title = "Neural Network Prediction of Censorable Language",
author = "Ng, Kei Yin and
Feldman, Anna and
Peng, Jing and
Leberknight, Chris",
booktitle = "Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2105",
doi = "10.18653/v1/W19-2105",
pages = "40--46",
abstract = "Internet censorship imposes restrictions on what information can be publicized or viewed on the Internet. According to Freedom House{'}s annual Freedom on the Net report, more than half the world{'}s Internet users now live in a place where the Internet is censored or restricted. China has built the world{'}s most extensive and sophisticated online censorship system. In this paper, we describe a new corpus of censored and uncensored social media tweets from a Chinese microblogging website, Sina Weibo, collected by tracking posts that mention {`}sensitive{'} topics or authored by {`}sensitive{'} users. We use this corpus to build a neural network classifier to predict censorship. Our model performs with a 88.50{\%} accuracy using only linguistic features. We discuss these features in detail and hypothesize that they could potentially be used for censorship circumvention.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ng-etal-2019-neural">
<titleInfo>
<title>Neural Network Prediction of Censorable Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kei</namePart>
<namePart type="given">Yin</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Feldman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Leberknight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-jun</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Internet censorship imposes restrictions on what information can be publicized or viewed on the Internet. According to Freedom House’s annual Freedom on the Net report, more than half the world’s Internet users now live in a place where the Internet is censored or restricted. China has built the world’s most extensive and sophisticated online censorship system. In this paper, we describe a new corpus of censored and uncensored social media tweets from a Chinese microblogging website, Sina Weibo, collected by tracking posts that mention ‘sensitive’ topics or authored by ‘sensitive’ users. We use this corpus to build a neural network classifier to predict censorship. Our model performs with a 88.50% accuracy using only linguistic features. We discuss these features in detail and hypothesize that they could potentially be used for censorship circumvention.</abstract>
<identifier type="citekey">ng-etal-2019-neural</identifier>
<identifier type="doi">10.18653/v1/W19-2105</identifier>
<location>
<url>https://aclanthology.org/W19-2105</url>
</location>
<part>
<date>2019-jun</date>
<extent unit="page">
<start>40</start>
<end>46</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Neural Network Prediction of Censorable Language
%A Ng, Kei Yin
%A Feldman, Anna
%A Peng, Jing
%A Leberknight, Chris
%S Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science
%D 2019
%8 jun
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F ng-etal-2019-neural
%X Internet censorship imposes restrictions on what information can be publicized or viewed on the Internet. According to Freedom House’s annual Freedom on the Net report, more than half the world’s Internet users now live in a place where the Internet is censored or restricted. China has built the world’s most extensive and sophisticated online censorship system. In this paper, we describe a new corpus of censored and uncensored social media tweets from a Chinese microblogging website, Sina Weibo, collected by tracking posts that mention ‘sensitive’ topics or authored by ‘sensitive’ users. We use this corpus to build a neural network classifier to predict censorship. Our model performs with a 88.50% accuracy using only linguistic features. We discuss these features in detail and hypothesize that they could potentially be used for censorship circumvention.
%R 10.18653/v1/W19-2105
%U https://aclanthology.org/W19-2105
%U https://doi.org/10.18653/v1/W19-2105
%P 40-46
Markdown (Informal)
[Neural Network Prediction of Censorable Language](https://aclanthology.org/W19-2105) (Ng et al., 2019)
ACL
- Kei Yin Ng, Anna Feldman, Jing Peng, and Chris Leberknight. 2019. Neural Network Prediction of Censorable Language. In Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science, pages 40–46, Minneapolis, Minnesota. Association for Computational Linguistics.