arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.20119cs.HC
收藏

具有时间意识的多模态(ZAM)数据集:关于促进进食障碍短视频的研究想法

Zeitgeist-Aware Multimodal (ZAM) Datasets of Pro-Eating Disorder Short-Form Videos: An Idea Worth Researching

Cornell University(康奈尔大学);The University of Tokyo(东京大学);Tohoku University(东北大学);The University of New South Wales (UNSW)(新南威尔士大学);University of Melbourne(墨尔本大学)

Eden Shaveet, Zefan Sramek, Yumi Hamamoto, Jing Du, Scott Griffiths, Thalia Zhang, Thalia Viranda, William Hornby, Flora Salim, Koji Yatani, Tanzeem Choudhury

AI总结:

本文提出ZAM数据集,旨在解决现有方法在识别促进进食障碍内容时的局限性,通过动态更新的多模态数据支持实时研究和模型训练。

摘要:

目的:可靠的在线识别促进进食障碍(pro-ED)内容面临两个普遍问题:1)现有方法主要依赖文本信号,无法捕捉多媒体内容的多模态本质;2)这些方法难以跟上参考、迷因、术语和上下文线索的快速演变。共同,这些限制指出了一个缺口:缺乏能够支持实时研究和稳健多模态检测模型训练的专家标注参考标准。方法:为了解决这一问题,我们提出了“时间意识”多模态(ZAM)数据集:持续编纂的标注多模态促进进食障碍内容集合,其纳入标准随着迷因时间意识演变:新媒体和参考进入文化时间意识并被在线空间吸收和解释。结果:我们提出了此类数据集的合理性,定义了其核心特征,概述了其编纂方法,并描述了我们的进展。讨论:此数据集和流水线架构可能受益于多个领域研究人员,他们关注促进进食障碍情绪如何通过短视频内容随时间编码和传播,包括为响应性管理努力的目的。

英文摘要:

Objective: Reliable identification of pro-eating disorder (pro-ED) content online suffers from two pervasive problems: 1) existing methods predominantly rely on text-based signals, failing to capture the inherently multimodal nature of multimedia content; and 2) these methods struggle to keep pace with the rapid evolution of references, memes, terminology, and contextual cues that underlie this content. Together, these limitations point to a gap: the absence of an expert-annotated reference standard capable of supporting real-time research and robust multimodal detection model training for pro-ED content on short-form video platforms. Method: To address this, we propose "zeitgeist-aware" multimodal (ZAM) datasets: continuously curated collections of annotated multimodal pro-ED content with inclusion criteria that evolve alongside the memetic zeitgeist: the variable essence of what is considered pro-ED as new media and references come into the cultural zeitgeist and are absorbed and interpreted in online spaces. Results: We present a rationale for such datasets, define their core characteristics, outline approaches for their curation, and describe our progress toward that end. Discussion: This dataset and pipeline architecture may benefit researchers across several fields who are interested in how pro-ED sentiment is encoded and transmitted through short-form video content across time, including for the purpose of responsive moderation efforts.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑