Supportiv, Berkeley, CA, United States.
JMIR Form Res. 2024 Oct 25;8:e59501. doi: 10.2196/59501.
Older adults have a high rate of loneliness, which contributes to increased psychosocial risk, medical morbidity, and mortality. Digital emotional support interventions provide a convenient and rapid avenue for additional support. Digital peer support interventions for emotional struggles contrast the usual provider-based clinical care models because they offer more accessible, direct support for empowerment, highlighting the users' autonomy, competence, and relatedness.
This study aims to examine a novel anonymous and synchronous peer-to-peer digital chat service facilitated by trained human moderators. The experience of a cohort of 699 adults aged ≥65 years was analyzed to determine (1) if participation, alone, led to measurable aggregate change in momentary loneliness and optimism and (2) the impact of peers on momentary loneliness and optimism.
Participants were each prompted with a single question: "What's your struggle?" Using a proprietary artificial intelligence model, the free-text response automatched the respondent based on their self-expressed emotional struggle to peers and a chat moderator. Exchanged messages were analyzed to quantitatively measure the change in momentary loneliness and optimism using a third-party, public, natural language processing model (GPT-4 [OpenAI]). The sentiment change analysis was initially performed at the individual level and then averaged across all users with similar emotion types to produce a statistically significant (P<.05) collective trend per emotion. To evaluate the peer impact on momentary loneliness and optimism, we performed propensity matching to align the moderator+single user and moderator+small group chat cohorts and then compare the emotion trends between the matched cohorts.
Loneliness and optimism trends significantly improved after 8 (P=.02) to 9 minutes (P=.03) into the chat. We observed a significant improvement in the momentary loneliness and optimism trends between the moderator+small group compared to the moderator+single user chat cohort after 19 (P=.049) and 21 minutes (P=.04) for optimism and loneliness, respectively.
Chat-based peer support may be a viable intervention to help address momentary loneliness in older adults and present an alternative to traditional care. The promising results support the need for further study to expand the evidence for such cost-effective options.
老年人的孤独感发生率很高，这会增加心理社会风险、增加发病率和死亡率。数字情感支持干预为额外的支持提供了便捷和快速的途径。数字同辈支持干预针对情感困扰，与通常的基于提供者的临床护理模式形成对比，因为它们为赋权提供了更易获得、更直接的支持，突出了用户的自主性、能力和相关性。
本研究旨在检查一种新颖的匿名和同步的由经过培训的人类主持人促成的同辈对辈数字聊天服务。分析了 699 名年龄≥65 岁的成年人的群组体验，以确定 (1) 仅参与是否会导致孤独感和乐观感的瞬间变化可衡量的总体变化，以及 (2) 同龄人的影响对瞬间孤独感和乐观感的影响。
每位参与者都被提示一个问题：“你的挣扎是什么？” 使用专有的人工智能模型，根据他们自我表达的情感挣扎，将回复自动匹配给同龄人以及聊天主持人。分析交换的消息，使用第三方、公共的自然语言处理模型（GPT-4 [OpenAI]）来定量衡量瞬间孤独感和乐观感的变化。情绪变化分析最初在个体层面进行，然后对具有相似情绪类型的所有用户进行平均，以产生每个情绪的具有统计学意义（P<.05）的集体趋势。为了评估同辈对瞬间孤独感和乐观感的影响，我们进行了倾向评分匹配，以对齐主持人+单个用户和主持人+小群体聊天队列，然后比较匹配队列之间的情绪趋势。
孤独感和乐观感的趋势在聊天 8 分钟（P=.02）到 9 分钟（P=.03）后显著改善。我们观察到，在主持人+小群体与主持人+单个用户聊天队列之间，乐观感和孤独感的情绪趋势在 19 分钟（P=.049）和 21 分钟（P=.04）后分别显著改善。
基于聊天的同辈支持可能是一种可行的干预措施，可以帮助解决老年人的瞬间孤独感，并为传统护理提供替代方案。有前途的结果支持需要进一步研究，以扩大此类具有成本效益的选择的证据。
