Using Innovative Machine Learning to Detect Organized Support and Opposition to E-cigarette Use Prevention Campaign Messaging on Twitter and TikTok

使用创新的机器学习来检测对电子烟使用的有组织的支持和反对 推特和TikTok上的预防运动信息 近年来，非卷烟烟草产品的消费急剧增加，包括电子烟。 产品或电子尼古丁输送系统(END)在很大程度上抵消了卷烟销量的显著下降 美国过去50年的吸烟率。作为回应，一些州、地方和联邦烟草公司 控制计划已经为青少年使用电子烟和电子烟制定了预防运动信息。一些人 其中一些运动也在社交媒体上激起了对减少烟草危害的强烈反对 倡导者。 强有力的证据支持反吸烟媒体运动在预防青少年吸烟方面的有效性 吸烟，但很少有研究考察旨在防止其他类型烟草的运动的影响 使用，例如反蒸发运动。此外，先前关于预防运动效果的证据并没有 考虑到当前混乱的媒体环境，竞选信息争夺受众 关注烟草产品推广信息，以及关于烟草产品的支持和反对信息 竞选活动本身。 因此，社交媒体干预以防止电子烟的使用是必要的，但潜力未知 在竞争激烈的通信环境中产生的影响，其特点是终端产品营销和 宣传，可能会导致受众困惑和错误信息。 因此，衡量社交媒体上电子烟使用预防活动的参与度 了解这种接触和信息流的模式是在 预防科学，并为烟草监管政策提供证据支持。拟议的项目将 评估电子烟使用预防相关内容的数量、覆盖范围和在社交媒体上的参与度(目标 1)；确定与支持和反对信息相关的来源和主要主题，使用 机器学习(目标2)；并应用社会网络理论和方法来研究社会网络的模式 媒体用户在竞选期间的信息寻找、曝光、传播和把关 时间(目标3)。

Using Innovative Machine Learning to Detect Organized Support and Opposition to E-cigarette Use Prevention Campaign Messaging on Twitter and TikTok In recent years sharp increases in the consumption of non-cigarette tobacco products, including vaping products or electronic nicotine delivery systems (ENDS), have largely offset the significant decline in cigarette smoking rates in the US over the past five decades. In response, several state, local and federal tobacco control programs have developed prevention campaign messages for youth vaping and e-cigarette use. Some of these campaigns have also provoked significant opposition on social media from tobacco harm reduction advocates. Strong evidence supports the effectiveness of anti-smoking media campaigns in preventing youth cigarette smoking, but little research has examined the effects of campaigns that aim to prevent other types of tobacco use, such as anti-vaping campaigns. Further, previous evidence about prevention campaign effects did not take into account the current cluttered media environment, where campaign messages compete for audience attention with tobacco product promotion messages and both supportive and oppositional messaging about the campaigns themselves. Thus, social media interventions to prevent e-cigarette use are necessary but have unknown potential effects in a competitive communication environment characterized by an influx of ENDS product marketing and advocacy, potentially resulting in audience confusion and misinformation. Therefore, measuring engagement with e-cigarette use prevention campaigns on social media and understanding the patterns of such engagement and information flow represent important advancements in the science of prevention and lend evidential support for tobacco regulatory policy. The proposed project will assess the e-cigarette use prevention-related content amount, reach, and engagement on social media (Aim 1); identify sources and major themes associated with both supportive and oppositional messages using machine learning (Aim 2); and apply social network theories and approaches to examine patterns of social media users’ information seeking, exposure, dissemination, and gatekeeping in the campaign periods over time (Aim 3).