@inproceedings{e4560f4527434e8fa6aaf99bf91d525c,
title = "Detecting censorable content on sina weibo: A pilot study",
abstract = "This study provides preliminary insights into the linguistic features that contribute to Internet censorship in mainland China. We collected a corpus of 344 censored and uncensored microblog posts that were published on Sina Weibo and built a Naive Bayes classifier based on the linguistic, topic-independent, features. The classifier achieves a 79.34% accuracy in predicting whether a blog post would be censored on Sina Weibo.",
keywords = "Chinese social media, censorship detection",
author = "Ng, {Kei Yin} and Anna Feldman and Chris Leberknight",
year = "2018",
month = jul,
day = "9",
doi = "10.1145/3200947.3201037",
language = "English",
series = "ACM International Conference Proceeding Series",
publisher = "Association for Computing Machinery",
booktitle = "Proceedings - 10th Hellenic Conference on Artificial Intelligence, SETN 2018",
note = "10th Hellenic Conference on Artificial Intelligence, SETN 2018 ; Conference date: 09-07-2018 Through 12-07-2018",
}