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

As the numbers of submissions to conferences grow quickly, the task ofassessing the quality of academic papers automatically, convincingly, and withhigh accuracy attracts increasing attention. We argue that studyinginterpretable dimensions of these submissions could lead to scalable solutions.We extract a collection of writing features, and construct a suite ofprediction tasks to assess the usefulness of these features in predictingcitation counts and the publication of AI-related papers. Depending on thevenues, the writing features can predict the conference vs. workshop appearancewith F1 scores up to 60-90, sometimes even outperforming the content-basedtf-idf features and RoBERTa. We show that the features describe writing stylemore than content. To further understand the results, we estimate the causalimpact of the most indicative features. Our analysis on writing featuresprovides a perspective to assessing and refining the writing of academicarticles at scale.

What do writing features tell us about AI papers?