Preliminary Evaluation of the Engagement and Effectiveness of a Mental Health Chatbot.
Preliminary Evaluation of the Engagement and Effectiveness of a Mental Health Chatbot.
复制标题
DOI：
10.3389/fdgth.2020.576361
复制
发表时间：
2020
影响因子：
--
通讯作者：
Kapps M
中科院分区：
文献类型：
--
作者：
Daley K;Hungerbuehler I;Cavanagh K;Claro HG;Swinton PA;Kapps M
背景：心理健康问题非常普遍，但获得支持的机会受到耻辱，成本和可用性的限制。这些问题在低收入和中等收入国家更为普遍，数字技术是克服这些障碍的一种潜在途径。数字化心理健康干预措施是有效的，但往往参与率低，特别是在缺乏人力支持的情况下。聊天机器人可以提供可扩展的解决方案，以较低的成本模拟人工支持。目的：完成对Vitalk（一种心理健康聊天机器人）在减少焦虑、抑郁和压力方面的参与度和有效性的初步评估。研究方法：研究人员分析了来自3,629名Vitalk用户的真实的世界数据，这些用户都完成了Vitalk项目的第一阶段（“减少焦虑”、“减少压力”或“改善情绪”）。程序是通过与聊天机器人的书面对话交付的。参与度是通过发送给聊天机器人的回复数量除以程序中的天数来计算的。结果：用户平均每天发送8.17个回复。对于所有三个项目，目标结果评分在基线和随访之间降低，其中焦虑（Cohen's d =-0.85），抑郁（Cohen's d =-0.91）和压力（Cohen's d =-0.81）的效应量较大。参与度的增加导致了焦虑和抑郁的干预后值的改善。结论：这项研究强调了聊天机器人在巴西普通人群中减少心理健康症状的潜力。虽然研究结果显示前景光明，但需要进一步研究。
Background: Mental health difficulties are highly prevalent, yet access to support is limited by barriers of stigma, cost, and availability. These issues are even more prevalent in low- and middle-income countries, and digital technology is one potential way to overcome these barriers. Digital mental health interventions are effective but often struggle with low engagement rates, particularly in the absence of human support. Chatbots could offer a scalable solution, simulating human support at a lower cost. Objective: To complete a preliminary evaluation of engagement and effectiveness of Vitalk, a mental health chatbot, at reducing anxiety, depression and stress. Methods: Real world data was analyzed from 3,629 Vitalk users who had completed the first phase of a Vitalk program (“less anxiety,” “less stress” or “better mood”). Programs were delivered through written conversation with a chatbot. Engagement was calculated from the number of responses sent to the chatbot divided by days in the program. Results: Users sent an average of 8.17 responses per day. For all three programs, target outcome scores reduced between baseline and follow up with large effect sizes for anxiety (Cohen's d = −0.85), depression (Cohen's d = −0.91) and stress (Cohen's d = −0.81). Increased engagement resulted in improved post-intervention values for anxiety and depression. Conclusion: This study highlights a chatbot's potential to reduce mental health symptoms in the general population within Brazil. While findings show promise, further research is required.