English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We present a method for generating synthetic versions of Twitter data usingneural generative models. The goal is protecting individuals in the source datafrom stylometric re-identification attacks while still releasing data thatcarries research value. Specifically, we generate tweet corpora that maintainuser-level word distributions by augmenting the neural language models withuser-specific components. We compare our approach to two standard text dataprotection methods: redaction and iterative translation. We evaluate the threemethods on measures of risk and utility. We define risk following thestylometric models of re-identification, and we define utility based on twogeneral word distribution measures and two common text analysis research tasks.We find that neural models are able to significantly lower risk over previousmethods with little cost to utility. We also demonstrate that the neural modelsallow data providers to actively control the risk-utility trade-off throughmodel tuning parameters. This work presents promising results for a new tooladdressing the problem of privacy for free text and sharing social media datain a way that respects privacy and is ethically responsible.

Using Neural Generative Models to Release Synthetic Twitter Corpora with Reduced Stylometric Identifiability of Users