The Benefits of Crowdsourcing to Seed and Align an Algorithm in an mHealth Intervention for African American and Hispanic Adults: Survey Study.
The Benefits of Crowdsourcing to Seed and Align an Algorithm in an mHealth Intervention for African American and Hispanic Adults: Survey Study.
复制标题
众包在非裔美国人和西班牙裔成年人的MHealth干预措施中播种和对齐算法的好处：调查研究。
DOI：
10.2196/30216
复制
发表时间：
2022-06-21
影响因子：
7.4
通讯作者：
Baur, Cynthia
中科院分区：
文献类型：
--
作者：
Sehgal, Neil Jay;Huang, Shuo;Johnson, Neil Mason;Dickerson, John;Jackson, Devlon;Baur, Cynthia
关键词：
对于非裔美国人和双语/西班牙语西班牙裔成年人的疾病预防和健康促进优先事项，缺乏公开且与文化相关的数据集，这对想要创建和测试基于这些优先事项并与这些优先事项保持一致的个性化工具的研究人员和开发人员来说是一个重大挑战。个性化取决于预测和性能数据。推荐系统 (RecSys) 可以预测与文化和个人最相关的预防性健康信息，并通过新颖的智能手机应用程序将其提供给非裔美国人和西班牙裔用户。然而，在用户体验的早期，RecSys 可能会面临“冷启动问题”，即在了解用户偏好之前提供未经定制和不相关的内容。对于服务不足的非裔美国人和西班牙裔人口来说，他们一直获得针对白人多数的健康内容，冷启动问题可能成为算法偏差的一个例子。为了避免这种情况，RecSys 需要符合应用程序用途的适合人群的种子数据。众包提供了一种生成适合人群的种子数据的方法。我们的目标是确定和测试一种方法，以解决缺乏特定文化的预防性个人健康数据的问题，并避免未在重点人群中接受过培训的 RecSys 固有的算法偏差类型。我们通过快速、低成本地从重点人群中收集大量数据来做到这一点，从而生成基于以预防为中心、与人群相关的健康目标的新颖数据集。我们使用 Amazon Mechanical Turk (MTurk) 将从自我认定的西班牙裔和自我认定的非西班牙裔非裔美国人/黑人成年受访者匿名收集的数据植入到 RecSys 中。 MTurk 为一项基于网络的调查提供了众包平台，其中受访者完成了个人资料和健康信息寻求评估，并提供了有关家庭健康史和个人健康史的数据。然后，受访者选择与可预防的健康状况相关的前 3 个健康目标，并针对每个目标，按重要性、个人效用、是否应将项目添加到个人健康库以及对返回信息质量的满意度来审查和评分前 3 个信息返回。本文报告了文章评级，因为我们的目的是评估众包种子 RecSys 的好处。对健康目标数据的分析将在未来的论文中报告。 MTurk 众包方法仅在 64 天内就从 485 名 (49%) 名自我认定的西班牙裔和 500 名 (51%) 名自我认定的非西班牙裔非裔美国成年人中生成了 985 份有效答复，每位受访者的成本为 6.74 美元。受访者对 92 篇独特的文章进行了评分，以向 RecSys 提供信息。研究人员可以选择 MTurk 等作为一种快速、低成本的方法来避免算法的冷启动问题，并避免偏见和与目标应用程序用户群体的低相关性。在 RecSys 中植入目标用户等人群的响应，可以开发数字健康工具，该工具可以根据类似的人口统计、健康目标和健康史向用户推荐信息。这种方法最大限度地减少了算法性能中潜在的、初始的差距；允许在使用中更快地改进算法；并且可以为寻求预防性健康信息以改善健康和实现健康目标的个人提供更好的用户体验。
The lack of publicly available and culturally relevant data sets on African American and bilingual/Spanish-speaking Hispanic adults’ disease prevention and health promotion priorities presents a major challenge for researchers and developers who want to create and test personalized tools built on and aligned with those priorities. Personalization depends on prediction and performance data. A recommender system (RecSys) could predict the most culturally and personally relevant preventative health information and serve it to African American and Hispanic users via a novel smartphone app. However, early in a user’s experience, a RecSys can face the “cold start problem” of serving untailored and irrelevant content before it learns user preferences. For underserved African American and Hispanic populations, who are consistently being served health content targeted toward the White majority, the cold start problem can become an example of algorithmic bias. To avoid this, a RecSys needs population-appropriate seed data aligned with the app’s purposes. Crowdsourcing provides a means to generate population-appropriate seed data. Our objective was to identify and test a method to address the lack of culturally specific preventative personal health data and sidestep the type of algorithmic bias inherent in a RecSys not trained in the population of focus. We did this by collecting a large amount of data quickly and at low cost from members of the population of focus, thereby generating a novel data set based on prevention-focused, population-relevant health goals. We seeded our RecSys with data collected anonymously from self-identified Hispanic and self-identified non-Hispanic African American/Black adult respondents, using Amazon Mechanical Turk (MTurk). MTurk provided the crowdsourcing platform for a web-based survey in which respondents completed a personal profile and a health information–seeking assessment, and provided data on family health history and personal health history. Respondents then selected their top 3 health goals related to preventable health conditions, and for each goal, reviewed and rated the top 3 information returns by importance, personal utility, whether the item should be added to their personal health library, and their satisfaction with the quality of the information returned. This paper reports the article ratings because our intent was to assess the benefits of crowdsourcing to seed a RecSys. The analysis of the data from health goals will be reported in future papers. The MTurk crowdsourcing approach generated 985 valid responses from 485 (49%) self-identified Hispanic and 500 (51%) self-identified non-Hispanic African American adults over the course of only 64 days at a cost of US $6.74 per respondent. Respondents rated 92 unique articles to inform the RecSys. Researchers have options such as MTurk as a quick, low-cost means to avoid the cold start problem for algorithms and to sidestep bias and low relevance for an intended population of app users. Seeding a RecSys with responses from people like the intended users allows for the development of a digital health tool that can recommend information to users based on similar demography, health goals, and health history. This approach minimizes the potential, initial gaps in algorithm performance; allows for quicker algorithm refinement in use; and may deliver a better user experience to individuals seeking preventative health information to improve health and achieve health goals.
登录
查看更多内容
影响因子：
6.1
作者：
Agapito, Giuseppe;Simeoni, Mariadelina;Cannataro, Mario
通讯作者：
Cannataro, Mario
影响因子：
1.9
作者：
Baur, Cynthia;Prue, Christine
通讯作者：
Prue, Christine
影响因子：
1.6
作者：
Burnham, Martin J.;Le, Yen K.;Piedmont, Ralph L.
通讯作者：
Piedmont, Ralph L.
影响因子：
12.6
作者：
Buhrmester, Michael;Kwang, Tracy;Gosling, Samuel D.
通讯作者：
Gosling, Samuel D.
影响因子：
8.8
作者：
Azadjalal, Mohammad Mandi;Moradi, Parham;Jalili, Mahdi
通讯作者：
Jalili, Mahdi