% 0期刊文章% @ 2564 - 1891 V %我JMIR出版物%卡塔尔世界杯8强波胆分析 N % P e42218 % 3% T的影响用户配置文件属性e-Cigarette-Related在YouTube上搜索:机器学习聚类和分类%没吃,李Dhiraj %, Juhan % Dashtian,哈桑%香港,恩典% +计算媒体实验室,新闻和媒体传播学院穆迪学院沟通,德克萨斯大学奥斯汀分校,300 W院长Keeton (A0900),奥斯汀,得克萨斯州,78712年,美国,1 512 471 5775,dhiraj.murthy@austin.utexas.edu % K电子香烟% K电子尼古丁交付系统% K结束% K烟草产品% K YouTube % K社交媒体% K少数民族% K暴露% K青年% K行为% K用户% K机器学习% K政策% D原始论文7 12.4.2023 % 9 2023% % J JMIR Infodemiology % G英语% X背景:由于电子烟的扩散在YouTube上的内容是有关,因为它可能影响青年使用行为。YouTube上有一个个性化的搜索和推荐算法属性来自用户的配置文件,比如年龄和性别。然而,对烟的内容是否显示不同的基于用户特征。摘要目的:本研究的目的是了解年龄和性别的影响属性e-cigarette-related YouTube的用户资料的搜索结果。方法:我们创建了16个虚构的YouTube概要文件与16岁和24年,性别(男性和女性),和民族/种族18 e-cigarette-related搜索条件搜索。我们使用无监督(k - means聚类和分类)和监督机器学习(图卷积网络)和网络分析来描述每个概要文件的搜索结果的变化。我们进一步检查用户属性是否可能发挥作用在e-cigarette-related内容暴露通过使用网络和学位中心。结果:我们分析了4201年nonduplicate视频。我们的k - means聚类显示视频可以集群分为3类。图像卷积网络实现精度高(0.72)。 Videos were classified based on content into 4 categories: product review (49.3%), health information (15.1%), instruction (26.9%), and other (8.5%). Underage users were exposed mostly to instructional videos (37.5%), with some indication that more female 16-year-old profiles were exposed to this content, while young adult age groups (24 years) were exposed mostly to product review videos (39.2%). Conclusions: Our results indicate that demographic attributes factor into YouTube’s algorithmic systems in the context of e-cigarette–related queries on YouTube. Specifically, differences in the age and sex attributes of user profiles do result in variance in both the videos presented in YouTube search results as well as in the types of these videos. We find that underage profiles were exposed to e-cigarette content despite YouTube’s age-restriction policy that ostensibly prohibits certain e-cigarette content. Greater enforcement of policies to restrict youth access to e-cigarette content is needed. %R 10.2196/42218 %U https://infodemiology.www.mybigtv.com/2023/1/e42218 %U https://doi.org/10.2196/42218