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

With the widespread use of toxic language online, platforms are increasinglyusing automated systems that leverage advances in natural language processingto automatically flag and remove toxic comments. However, most automatedsystems -- when detecting and moderating toxic language -- do not providefeedback to their users, let alone provide an avenue of recourse for theseusers to make actionable changes. We present our work, RECAST, an interactive,open-sourced web tool for visualizing these models' toxic predictions, whileproviding alternative suggestions for flagged toxic language. Our work alsoprovides users with a new path of recourse when using these automatedmoderation tools. RECAST highlights text responsible for classifying toxicity,and allows users to interactively substitute potentially toxic phrases withneutral alternatives. We examined the effect of RECAST via two large-scale userevaluations, and found that RECAST was highly effective at helping users reducetoxicity as detected through the model. Users also gained a strongerunderstanding of the underlying toxicity criterion used by black-box models,enabling transparency and recourse. In addition, we found that when users focuson optimizing language for these models instead of their own judgement (whichis the implied incentive and goal of deploying automated models), these modelscease to be effective classifiers of toxicity compared to human annotations.This opens a discussion for how toxicity detection models work and should work,and their effect on the future of online discourse.

RECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization