{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T11:06:46Z","timestamp":1785236806159,"version":"3.55.0"},"reference-count":35,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100006749","name":"burapha university","doi-asserted-by":"publisher","award":["HUSO05\/2567"],"award-info":[{"award-number":["HUSO05\/2567"]}],"id":[{"id":"10.13039\/501100006749","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Information Science"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:p>The quality of metadata is critical for the effective organisation, retrieval and management of increasingly large repositories of AI-generated images. However, the absence of inherent contextual information in such images presents significant challenges in ensuring accurate and relevant metadata. This study evaluates the effectiveness of generative AI and image recognition approaches in improving metadata quality, based on 10 comprehensive criteria: semantic accuracy and relevance; thematic consistency and contextual adaptability; user-centric language and accessibility; consistency across data sets; emotional and aesthetic alignment; inclusivity and bias control; error detection and quality control; retrievability and search optimization; interpretive depth and granularity; and statistical performance measures. Results reveal that generative AI is particularly effective in generating contextually rich, adaptive keywords, while image recognition demonstrates superior object identification precision. Based on these insights, we propose a hybrid approach that integrates the contextual strengths of generative AI with the accuracy of image recognition. This hybrid method achieves significant improvements across all evaluations, including higher precision, recall, F1-score, cosine similarity and Jaccard index. By optimising metadata quality, the proposed approach facilitates more accurate and accessible retrieval of AI-generated images, significantly enhancing their usability and integration across diverse digital platforms.<\/jats:p>","DOI":"10.1177\/01655515251397636","type":"journal-article","created":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T06:52:28Z","timestamp":1766818348000},"page":"1059-1074","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Assessing and optimising metadata quality for AI-generated images: A comparative analysis of generative AI and image recognition approaches"],"prefix":"10.1177","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7006-0883","authenticated-orcid":false,"given":"Akara","family":"Thammastitkul","sequence":"first","affiliation":[{"name":"Department of Information Studies, Faculty of Humanities and Social Sciences, Burapha University, Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,12,26]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2013.05.003"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1177\/09610006241239080"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1177\/21582440231201368"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1177\/01655515221142428"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/MDM48529.2020.00074"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1177\/0165551521998045"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.21533\/pen.v11.i2.110"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2208839120"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9100199"},{"issue":"3","key":"e_1_3_3_11_2","first-page":"243","article-title":"Unanticipating metadata: metadata in the ages of the internet and AI","volume":"43","author":"Weinberger D","year":"2023","unstructured":"Weinberger D, Lawlor B. Unanticipating metadata: metadata in the ages of the internet and AI. Inf Serv Use 2023; 43(3\u20134): 243\u2013247.","journal-title":"Inf Serv Use"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging7080121"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/QoMEX58391.2023.10178486"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.11591\/ijai.v13.i2.pp1294-1303"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2005.50"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.foodqual.2024.105149"},{"issue":"3","key":"e_1_3_3_17_2","first-page":"17246","article-title":"Exploring the impact of generative artificial intelligence on higher education students\u2019 utilization of library resources: a critical examination","volume":"43","author":"Meakin L.","year":"2024","unstructured":"Meakin L. Exploring the impact of generative artificial intelligence on higher education students\u2019 utilization of library resources: a critical examination. Inf Technol Libr 2024; 43(3): 17246.","journal-title":"Inf Technol Libr"},{"key":"e_1_3_3_18_2","first-page":"53","article-title":"Review of AI image generator: influences, challenges, and future prospects for architectural field","volume":"2","author":"Enjellina Beyan E","year":"2023","unstructured":"Enjellina Beyan E, Rossy A. Review of AI image generator: influences, challenges, and future prospects for architectural field. J Artif Intell Arch 2023; 2: 53\u201365.","journal-title":"J Artif Intell Arch"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3356122"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1162\/dint_a_00189"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2024.03.039"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.35940\/ijitee.K7732.0991120"},{"issue":"2","key":"e_1_3_3_23_2","first-page":"23","article-title":"Text mining and automatic short answer grading (ASAG): comparison of three methods of cosine similarity, Jaccard similarity, and Dice\u2019s coefficient","volume":"2","author":"Wahyuningsih T","year":"2021","unstructured":"Wahyuningsih T, Henderi H, Winarno W. Text mining and automatic short answer grading (ASAG): comparison of three methods of cosine similarity, Jaccard similarity, and Dice\u2019s coefficient. J Data Sci Syst 2021; 2(2): 23\u201334.","journal-title":"J Data Sci Syst"},{"key":"e_1_3_3_24_2","first-page":"20","article-title":"The role of AI in transforming metadata management: insights on challenges, opportunities, and emerging trends","volume":"14","author":"Oyighan D","year":"2024","unstructured":"Oyighan D, Ukubeyinje E, David-West B, et al. The role of AI in transforming metadata management: insights on challenges, opportunities, and emerging trends. Asian J Inf Sci Technol 2024; 14: 20\u201326.","journal-title":"Asian J Inf Sci Technol"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/educsci13090856"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/MIC.2024.3377170"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1177\/01655515221114452"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpos.2023.1245684"},{"key":"e_1_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Storch H. Collection insight and interconnectivity through artificial intelligence image analysis: a collaboration with the National Archives of Estonia. J Digit Media Manag 2023; 12(1): 35\u201345. https:\/\/doi.org\/10.69554\/ICOI3279","DOI":"10.69554\/ICOI3279"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.2196\/59914"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.3390\/informatics9020038"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCE.2024.3474037"},{"key":"e_1_3_3_33_2","unstructured":"Copilot Designer. Create images from words with AI 2024. https:\/\/copilot.microsoft.com\/images\/create"},{"key":"e_1_3_3_34_2","unstructured":"Pixited. Showcase for art generated by AI and you 2024. https:\/\/www.pixited.com\/"},{"key":"e_1_3_3_35_2","unstructured":"Freepik. Smarter creativity faster designs 2024. https:\/\/www.freepik.com\/"},{"key":"e_1_3_3_36_2","unstructured":"Google Cloud. Cloud vision API 2024. https:\/\/cloud.google.com\/vision\/"}],"container-title":["Journal of Information Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01655515251397636","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/01655515251397636","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/01655515251397636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T10:50:44Z","timestamp":1785235844000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/01655515251397636"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,26]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1177\/01655515251397636"],"URL":"https:\/\/doi.org\/10.1177\/01655515251397636","relation":{},"ISSN":["0165-5515","1741-6485"],"issn-type":[{"value":"0165-5515","type":"print"},{"value":"1741-6485","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,26]]}}}