{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T09:05:24Z","timestamp":1779267924012,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,26]]},"DOI":"10.1145\/3795766.3799742","type":"proceedings-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T07:50:03Z","timestamp":1779263403000},"page":"108-112","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpreting Short Social Media Videos with Multimodal LLMs: A Validation Experiment"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8478-4540","authenticated-orcid":false,"given":"Sandy","family":"Liu","sequence":"first","affiliation":[{"name":"Wellesley College, Wellesley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5617-1779","authenticated-orcid":false,"given":"Ella","family":"Haig","sequence":"additional","affiliation":[{"name":"University of Portsmouth, Southsea, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2243-5892","authenticated-orcid":false,"given":"Eni","family":"Mustafaraj","sequence":"additional","affiliation":[{"name":"Wellesley College, Wellesley, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3717867.3717881"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01719"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-61057-8_31"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02245"},{"key":"e_1_3_3_2_6_2","volume-title":"Proceedings of NeurIPS","author":"Guerdan Luke","year":"2025","unstructured":"Luke Guerdan, Solon Barocas, Ken Holstein, Hanna Wallach, Steven Wu, and Alexandra Chouldechova. 2025. Validating LLM-as-a-Judge Systems under Rating Indeterminacy. In Proceedings of NeurIPS."},{"key":"e_1_3_3_2_7_2","unstructured":"Chihcheng Hsieh Catarina Moreira Isabel\u00a0Blanco Nobre Sandra\u00a0Costa Sousa Chun Ouyang Margot Brereton Joaquim Jorge and Jacinto\u00a0C Nascimento. 2024. Dall-m: Context-aware clinical data augmentation with llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.08227 (2024)."},{"key":"e_1_3_3_2_8_2","unstructured":"Md\u00a0Saroar Jahan Mourad Oussalah Djamila\u00a0Romaissa Beddia Nabil Arhab et\u00a0al. 2024. A comprehensive study on nlp data augmentation for hate speech detection: Legacy methods bert and llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.00303 (2024)."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Nicolas\u00a0M Legewie and Anne Nassauer. 2023. Current and future debates in video data analysis. Sociological Methods & Research 52 3 (2023) 1107\u20131119.","DOI":"10.1177\/00491241231178275"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3726302.3729917"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Ronghao Lin and Haifeng Hu. 2024. Adapt and explore: Multimodal mixup for representation learning. Information Fusion 105 (2024) 102216.","DOI":"10.1016\/j.inffus.2023.102216"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Laura\u00a0K Nelson. 2020. Computational grounded theory: A methodological framework. Sociological methods & research 49 1 (2020) 3\u201342.","DOI":"10.1177\/0049124117729703"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Jesus Perez-Martin Benjamin Bustos Silvio Jamil\u00a0F Guimar\u00e3es Ivan Sipiran Jorge P\u00e9rez and Grethel\u00a0Coello Said. 2022. A comprehensive review of the video-to-text problem. Artificial Intelligence Review 55 5 (2022) 4165\u20134239.","DOI":"10.1007\/s10462-021-10104-1"},{"key":"e_1_3_3_2_14_2","unstructured":"Ranjan Sapkota Shaina Raza Maged Shoman Achyut Paudel and Manoj Karkee. 2025. Multimodal large language models for image text and speech data augmentation: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.18648 (2025)."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Connor Shorten Taghi\u00a0M Khoshgoftaar and Borko Furht. 2021. Text data augmentation for deep learning. Journal of big Data 8 1 (2021) 101.","DOI":"10.1186\/s40537-021-00492-0"},{"key":"e_1_3_3_2_16_2","unstructured":"Rebecca\u00a0L Stotzer and Ashley Nelson. 2025. The allure of traditional life: on becoming a tradwife. Journal of Gender Studies (2025) 1\u201318."},{"key":"e_1_3_3_2_17_2","unstructured":"Yunlong Tang Jing Bi Siting Xu Luchuan Song Susan Liang Teng Wang Daoan Zhang Jie An Jingyang Lin Rongyi Zhu et\u00a0al. 2025. Video understanding with large language models: A survey. IEEE Transactions on Circuits and Systems for Video Technology (2025)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3614419.3644023"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Haomiao Xiong Yunzhi Zhuge Jiawen Zhu Lu Zhang and Huchuan Lu. 2025. 3ur-llm: An end-to-end multimodal large language model for 3d scene understanding. IEEE Transactions on Multimedia (2025) 2899\u20132911.","DOI":"10.1109\/TMM.2025.3557620"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Shukang Yin Chaoyou Fu Sirui Zhao Ke Li Xing Sun Tong Xu and Enhong Chen. 2024. A survey on multimodal large language models. National Science Review 11 12 (2024) nwae403.","DOI":"10.1093\/nsr\/nwae403"},{"key":"e_1_3_3_2_21_2","first-page":"1324","volume-title":"AMIA Annual Symposium Proceedings","author":"Yuan Jiayi","year":"2024","unstructured":"Jiayi Yuan, Ruixiang Tang, Xiaoqian Jiang, and Xia Hu. 2024. Large language models for healthcare data augmentation: An example on patient-trial matching. In AMIA Annual Symposium Proceedings. 1324\u20131333."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Lingxuan Zhu Weiming Mou Chenglin Hong Tao Yang Yancheng Lai Chang Qi Anqi Lin Jian Zhang and Peng Luo. 2024. The evaluation of generative AI should include repetition to assess stability. JMIR mHealth and uHealth 12 (2024).","DOI":"10.2196\/57978"}],"event":{"name":"WebSci '26: 18th ACM Web Science Conference 2026","location":"Braunschweig Germany","acronym":"WebSci '26","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 18th ACM Web Science Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3795766.3799742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T08:06:15Z","timestamp":1779264375000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3795766.3799742"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":22,"alternative-id":["10.1145\/3795766.3799742","10.1145\/3795766"],"URL":"https:\/\/doi.org\/10.1145\/3795766.3799742","relation":{},"subject":[],"published":{"date-parts":[[2026,5,25]]},"assertion":[{"value":"2026-05-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}