{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T00:46:16Z","timestamp":1760575576179,"version":"build-2065373602"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIES"],"abstract":"<jats:p>The plethora of fairness metrics  developed for\nranking-based decision-making raises the question which\nmetrics align best with people\u2019s perceptions of fairness,\nand why? Most prior studies examining people\u2019s perceptions\nof fairness metrics tend to use ordinal rating scales\n(e.g., Likert scales). However, such scales can be\nambiguous in their interpretation across participants and\noffer imprecise connections to specific interface features.\nWe address this gap by adapting two-alternative forced\nchoice methodologies\u2014used extensively outside the fairness\ncommunity for comparing visual stimuli\u2014to quantitatively\ncompare participant perceptions, fairness metrics, and\nranking characteristics. We report a crowdsourced\nexperiment with 224 participants across four conditions:\ntwo popular rank fairness metrics\u2014ARP and NDKL\u2014and two\nranking characteristics\u2014lists of 20 and 100\ncandidates\u2014resulting in over 170,000 individual judgments.\nOur quantitative results show systematic patterns of\ndifferences in the metrics, as well as surprising\nexceptions where fairness metrics disagree with people\u2019s\nperceptions. Our qualitative analysis reveals an interplay\nbetween cognitive and visual strategies that affects\npeople\u2019s perceptions of fairness. From these results, we\ndiscuss future work in aligning fairness metrics with\npeople\u2019s perceptions, and highlight the need and benefits\nof expanding methodologies for fairness studies.<\/jats:p>","DOI":"10.1609\/aies.v8i1.36532","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:16:28Z","timestamp":1760534188000},"page":"76-89","source":"Crossref","is-referenced-by-count":0,"title":["Exploring \u201cJust Noticeable\u201d Group Fairness in Rankings"],"prefix":"10.1609","volume":"8","author":[{"given":"Mallak","family":"Alkhathlan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hilson","family":"Shrestha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lane","family":"Harrison","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elke","family":"Rundensteiner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"9382","published-online":{"date-parts":[[2025,10,15]]},"container-title":["Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36532\/38670","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36532\/38670","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:16:28Z","timestamp":1760534188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/view\/36532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":0,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,10,15]]}},"URL":"https:\/\/doi.org\/10.1609\/aies.v8i1.36532","relation":{},"ISSN":["3065-8365"],"issn-type":[{"value":"3065-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}