Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Linguistic Fingerprints of Internet Censorship: The Case of Sina Weibo
Authors: Kei Yin Ng, Anna Feldman, Jing Peng446-453
AAAI 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We build a classifier that significantly outperforms non-expert humans in predicting whether a blogpost will be censored. Our best results are over 30% higher than the baseline and about 60% higher than the human baseline obtained through crowdsourcing, which shows that our classifier has a greater censorship predictive ability compared to human judgments. |
| Researcher Affiliation | Academia | Kei Yin Ng, Anna Feldman, Jing Peng Montclair State University Montclair, New Jersey, USA |
| Pseudocode | No | The paper describes the methodologies in prose but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about releasing open-source code for the described methodology, nor does it include a link to a code repository. |
| Open Datasets | Yes | Using Zhu et al. (2003) s Corpus; Zhu et al. (2013) collected over 2 million posts published by a set of around 3,500 sensitive users during a 2-month period in 2012. |
| Dataset Splits | Yes | Each experiment is validated with 10-fold cross validation. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions several tools and libraries used (e.g., LIWC, Baidu AI, CRIE, word2vec, Jieba Part-of-speech tagger), but it does not specify version numbers for these software components, which is required for reproducibility. |
| Experiment Setup | Yes | The rest of the parameters are set to default learning rate of 0.3, momentum of 0.2, batch size of 100, validation threshold of 20. |