• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

运用主题建模和定性内容分析来识别和描述 Instagram 上电子烟产品的促销和销售情况。

Applying topic modelling and qualitative content analysis to identify and characterise ENDS product promotion and sales on Instagram.

机构信息

Department of Healthcare Research and Policy, University of California San Diego, La Jolla, California, USA.

Global Health Policy and Data Institute, San Diego, California, USA.

出版信息

Tob Control. 2023 Aug;32(e2):e153-e159. doi: 10.1136/tobaccocontrol-2021-056937. Epub 2021 Dec 2.

DOI:10.1136/tobaccocontrol-2021-056937
PMID:34857646
Abstract

BACKGROUND

Increased public health and regulatory scrutiny concerning the youth vaping epidemic has led to greater attention to promotion and sales of vaping products on social media platforms.

OBJECTIVES

We used unsupervised machine learning to identify and characterise sale offers of electronic nicotine delivery systems (ENDS) and associated products on Instagram. We examined types of sellers, geographic ENDS location and use of age verification.

METHODS

Our methodology was composed of three phases: data collection, topic modelling and content analysis. We used data mining approaches to query hashtags related to ENDS product use among young adults to collect Instagram posts. For topic modelling, we applied an unsupervised machine learning approach to thematically categorise and identify topic clusters associated with selling activity. Content analysis was then used to characterise offers for sale of ENDS products.

RESULTS

From 70 725 posts, we identified 3331 engaged in sale of ENDS products. Posts originated from 20 different countries and were roughly split between individual (46.3%) and retail sellers (43.4%), with linked online sellers (8.8%) representing a smaller volume. ENDS products most frequently offered for sale were flavoured e-liquids (53.0%) and vaping devices (20.5%). Online sellers offering flavoured e-liquids were less likely to use age verification at point of purchase (29% vs 64%) compared with other products.

CONCLUSIONS

Instagram is a global venue for unregulated ENDS sales, including flavoured products, and access to websites lacking age verification. Such posts may violate Instagram's policies and US federal and state law, necessitating more robust review and enforcement to prevent ENDS uptake and access.

摘要

背景

公众健康意识和监管审查力度的增强,使人们对社交媒体平台上电子烟产品的推广和销售越发关注。

目的

我们使用无监督机器学习来识别和描述 Instagram 上电子烟(ENDS)及其相关产品的销售信息。我们检查了销售者的类型、ENDS 的地理位置和年龄验证的使用情况。

方法

我们的方法由三个阶段组成:数据收集、主题建模和内容分析。我们使用数据挖掘方法查询与年轻人使用 ENDS 产品相关的标签,以收集 Instagram 帖子。对于主题建模,我们应用了一种无监督机器学习方法,对与销售活动相关的主题集群进行分类和识别。然后,使用内容分析来描述销售 ENDS 产品的信息。

结果

从 70725 条帖子中,我们确定了 3331 条与销售 ENDS 产品有关的帖子。这些帖子来自 20 个不同的国家,大致分为个人卖家(46.3%)和零售商(43.4%),而链接的在线卖家(8.8%)则代表了较小的一部分。最常销售的 ENDS 产品是调味电子烟液(53.0%)和电子烟设备(20.5%)。与其他产品相比,销售调味电子烟液的在线卖家在购买时更不可能使用年龄验证(29%比 64%)。

结论

Instagram 是一个不受监管的 ENDS 销售场所,包括调味产品,并且可以访问缺乏年龄验证的网站。这些帖子可能违反了 Instagram 的政策以及美国联邦和州的法律,需要更严格的审查和执行,以防止年轻人使用电子烟。

相似文献

1
Applying topic modelling and qualitative content analysis to identify and characterise ENDS product promotion and sales on Instagram.运用主题建模和定性内容分析来识别和描述 Instagram 上电子烟产品的促销和销售情况。
Tob Control. 2023 Aug;32(e2):e153-e159. doi: 10.1136/tobaccocontrol-2021-056937. Epub 2021 Dec 2.
2
Identification and Characterization of Synthetic Nicotine Product Promotion and Sales on Instagram Using Natural Language Processing.使用自然语言处理技术识别和表征Instagram上合成尼古丁产品的推广与销售情况
Nicotine Tob Res. 2024 Apr 22;26(5):580-588. doi: 10.1093/ntr/ntad222.
3
Industry response to strengthened regulations: amount and themes of flavoured electronic cigarette promotion by product vendors and manufacturers on Instagram.行业对加强监管的反应:产品销售商和制造商在 Instagram 上推广调味电子烟的数量和主题。
Tob Control. 2022 Nov;31(Suppl 3):s249-s254. doi: 10.1136/tc-2022-057490.
4
Vaping and Instagram: A Content Analysis of e-Cigarette Posts Using the Content Appealing to Youth (CAY) Index.吸电子烟和 Instagram:使用吸引年轻人内容(CAY)指数对电子烟帖子进行的内容分析。
Subst Use Misuse. 2021;56(6):879-887. doi: 10.1080/10826084.2021.1899233. Epub 2021 Mar 22.
5
Big Data, Natural Language Processing, and Deep Learning to Detect and Characterize Illicit COVID-19 Product Sales: Infoveillance Study on Twitter and Instagram.大数据、自然语言处理和深度学习技术在检测和识别非法销售 COVID-19 产品中的应用:对 Twitter 和 Instagram 的 Infoveillance 研究。
JMIR Public Health Surveill. 2020 Aug 25;6(3):e20794. doi: 10.2196/20794.
6
Identification and Characterization of Illegal Sales of Cannabis and Nicotine Delivery Products on Telegram Messaging Platform.Telegram 即时通讯平台上大麻和尼古丁递送产品非法销售的识别与特征分析
Nicotine Tob Res. 2024 May 22;26(6):771-779. doi: 10.1093/ntr/ntad248.
7
Characterising JUUL-related posts on Instagram.描述 Instagram 上与 JUUL 相关的帖子。
Tob Control. 2020 Nov;29(6):612-617. doi: 10.1136/tobaccocontrol-2018-054824. Epub 2019 Jul 2.
8
From Apple to Werewolf: A content analysis of marketing for e-liquids on Instagram.从苹果到狼人:对 Instagram 上电子烟油营销的内容分析。
Addict Behav. 2019 Apr;91:119-127. doi: 10.1016/j.addbeh.2018.09.008. Epub 2018 Sep 9.
9
Electronic nicotine delivery systems (ENDS) flavours and devices used by adults before and after the 2020 US FDA ENDS enforcement priority: findings from the 2018 and 2020 US ITC Smoking and Vaping Surveys.电子尼古丁传送系统(ENDS)口味和装置在 2020 年美国 FDA 加强 ENDS 监管力度前后被成年人使用的情况:来自 2018 年和 2020 年美国 ITC 吸烟与蒸气调查的结果。
Tob Control. 2022 Nov;31(Suppl 3):s167-s175. doi: 10.1136/tobaccocontrol-2022-057445.
10
Characterizing vaping posts on Instagram by using unsupervised machine learning.利用无监督机器学习对 Instagram 上的 vaping 帖子进行特征描述。
Int J Med Inform. 2020 Sep;141:104223. doi: 10.1016/j.ijmedinf.2020.104223. Epub 2020 Jun 20.

引用本文的文献

1
Harnessing machine learning in contemporary tobacco research.当代烟草研究中机器学习的应用
Toxicol Rep. 2024 Dec 19;14:101877. doi: 10.1016/j.toxrep.2024.101877. eCollection 2025 Jun.
2
Multidisciplinary approaches in electronic nicotine delivery systems pulmonary toxicology: emergence of living and non-living bioinspired engineered systems.电子尼古丁传送系统肺毒理学中的多学科方法:生物启发的活体和非活体工程系统的出现
Commun Eng. 2024 Sep 3;3(1):123. doi: 10.1038/s44172-024-00276-3.
3
Young Adults' Exposure to and Engagement With Tobacco-Related Social Media Content and Subsequent Tobacco Use.
年轻人接触和参与与烟草相关的社交媒体内容与随后的烟草使用。
Nicotine Tob Res. 2024 Feb 15;26(Supplement_1):S3-S12. doi: 10.1093/ntr/ntad108.
4
Topic prediction for tobacco control based on COP9 tweets using machine learning techniques.基于机器学习技术的 COP9 推特点的烟草控制主题预测。
PLoS One. 2024 Feb 15;19(2):e0298298. doi: 10.1371/journal.pone.0298298. eCollection 2024.
5
Detecting nuance in conspiracy discourse: Advancing methods in infodemiology and communication science with machine learning and qualitative content coding.检测阴谋话语中的细微差别:用机器学习和定性内容编码推进信息流行病学和传播学方法。
PLoS One. 2023 Dec 20;18(12):e0295414. doi: 10.1371/journal.pone.0295414. eCollection 2023.
6
Identification and Characterization of Synthetic Nicotine Product Promotion and Sales on Instagram Using Natural Language Processing.使用自然语言处理技术识别和表征Instagram上合成尼古丁产品的推广与销售情况
Nicotine Tob Res. 2024 Apr 22;26(5):580-588. doi: 10.1093/ntr/ntad222.
7
Implications of nicotine vaping products for tobacco control in ASEAN low-income and middle-income countries: in-depth interviews with experts from the region.尼古丁电子烟产品对东盟中低收入国家烟草控制的影响:对该地区专家的深入访谈。
BMJ Open. 2023 Sep 19;13(9):e073106. doi: 10.1136/bmjopen-2023-073106.
8
Broad range of research on e-cigarettes.关于电子烟的广泛研究。
Tob Control. 2023 Aug;32(e2):e137-e138. doi: 10.1136/tc-2023-058209.
9
Assessing Characteristics and Compliance of Online Delta-8 Tetrahydrocannabinol Product Sellers.评估在线 Delta-8 四氢大麻酚产品销售商的特征和合规性。
Cannabis Cannabinoid Res. 2024 Aug;9(4):e1132-e1141. doi: 10.1089/can.2022.0341. Epub 2023 May 17.
10
Public Figure Vaccination Rhetoric and Vaccine Hesitancy: Retrospective Twitter Analysis.公众人物的疫苗接种言论与疫苗犹豫:推特回顾性分析
JMIR Infodemiology. 2023 Mar 10;3:e40575. doi: 10.2196/40575. eCollection 2023.