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

Multi-modal search engines have experienced significant growth and widespreaduse in recent years, making them the second most common internet use. Whilesearch engine systems offer a range of services, the image search field hasrecently become a focal point in the information retrieval community, as theadage goes, "a picture is worth a thousand words". Although popular searchengines like Google excel at image search accuracy and agility, there is anongoing debate over whether their search results can be biased in terms ofgender, language, demographics, socio-cultural aspects, and stereotypes. Thispotential for bias can have a significant impact on individuals' perceptionsand influence their perspectives.  In this paper, we present our study on bias and fairness in web search, witha focus on keyword-based image search. We first discuss several kinds of biasesthat exist in search systems and why it is important to mitigate them. Wenarrow down our study to assessing and mitigating occupational stereotypes inimage search, which is a prevalent fairness issue in image retrieval. For theassessment of stereotypes, we take gender as an indicator. We explore variousopen-source and proprietary APIs for gender identification from images. Withthese, we examine the extent of gender bias in top-tanked image search resultsobtained for several occupational keywords. To mitigate the bias, we thenpropose a fairness-aware re-ranking algorithm that optimizes (a) relevance ofthe search result with the keyword and (b) fairness w.r.t genders identified.We experiment on 100 top-ranked images obtained for 10 occupational keywordsand consider random re-ranking and re-ranking based on relevance as baselines.Our experimental results show that the fairness-aware re-ranking algorithmproduces rankings with better fairness scores and competitive relevance scoresthan the baselines.

Fairness in Image Search: A Study of Occupational Stereotyping in Image Retrieval and its Debiasing