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

User-generated reviews of products are vital assets of online commerce, suchas Amazon and Yelp, while fake reviews are prevalent to mislead customers. GNNis the state-of-the-art method that detects suspicious reviewers by exploitingthe topologies of the graph connecting reviewers, reviews, and target products.However, the discrepancy in the detection accuracy over different groups ofreviewers can degrade reviewer engagement and customer trust in the reviewwebsites. Unlike the previous belief that the difference between the groupscauses unfairness, we study the subgroup structures within the groups that canalso cause discrepancies in treating different groups. This paper addresses thechallenges of defining, approximating, and utilizing a new subgroup structurefor fair spam detection. We first identify subgroup structures in the reviewgraph that lead to discrepant accuracy in the groups. The complex dependenciesover the review graph create difficulties in teasing out subgroups hiddenwithin larger groups. We design a model that can be trained to jointly inferthe hidden subgroup memberships and exploits the membership for calibrating thedetection accuracy across groups. Comprehensive comparisons against baselineson three large Yelp review datasets demonstrate that the subgroup membershipcan be identified and exploited for group fairness.

Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detection