Supporting Student Mental Health With the Safespace Generative AI Chatbot: A Mixed-Methods Feasibility Study

作者
Matteo Pinna,Sergio Galletta,Elliott Ash,Timon Elmer
标识
DOI:10.31234/osf.io/g39t5_v1
摘要

Background: Generative Artificial Intelligence (genAI) chatbots have the potential to provide personalized mental health support to individuals at scale.Objective: This study evaluates the feasibility and usage patterns of the Safespace genAI chatbot, an AI-driven smartphone application that offers an LLM-powered interactive chatbot to support mental health.Methods: Using a mixed-methods approach, we explored baseline attitudes towards genAI chatbots and chatbot usage patterns, conducted a qualitative content analysis of participants’ experiences, and descriptively assessed patterns related to pre-intervention depressive symptoms. The study included an initial sample of N = 42 university students, n = 20 of whom actively used the chatbot over two to four weeks, generating 286 user-chatbot interactions.Results: Pre-intervention surveys indicated that the majority of participants anticipated the chatbot would be helpful (64%) and that they trusted its privacy safeguards (93%). Usage patterns hinted towards that the highest levels of interaction occurred early in the morning and late at night, when peer and professional support may be inaccessible. The qualitative analysis indicated that participants appreciated using the chatbot for reflection as a blended care tool between their counseling sessions, while also naming technical barriers and specific design needs to sustain engagement. In addition, our exploratory analyses descriptively showed that participants with elevated depression scores engaged in emotional disclosure during 99% of their sessions, compared to 84% for those with low symptoms. Due to the small sample size, future adequately powered studies are needed to inferentially examine these observed patterns.Conclusion: These findings provide initial insights into the usage and engagement dynamics of the Safespace genAI chatbot and highlight directions for future research to optimize genAI-driven mental health interventions.Trial Registration: AEA Registry https://doi.org/10.1257/rct.13291-1.0

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
李昱成发布了新的文献求助10
刚刚
大模型的应助被sapphire采纳,获得30
刚刚
waui完成签到 ,获得积分10
刚刚
就酱完成签到,获得积分10
1秒前
1秒前
天师热风发布了新的文献求助10
1秒前
hlbbb的应助被袁rrrr采纳,获得10
2秒前
可爱的函函的应助被林夕采纳,获得10
2秒前
科研通AI6.2的应助被chenxueneng采纳,获得10
2秒前
英姑的应助被qq大魔王采纳,获得100
2秒前
2秒前
kiko的应助被qq大魔王采纳,获得100
2秒前
在水一方的应助被qq大魔王采纳,获得100
3秒前
科研通AI2S的应助被qq大魔王采纳,获得10
3秒前
kiko的应助被qq大魔王采纳,获得100
3秒前
小刘完成签到,获得积分10
3秒前
kiko的应助被qq大魔王采纳,获得100
3秒前
3秒前
Orange的应助被qq大魔王采纳,获得10
3秒前
加油鸭发布了新的文献求助10
4秒前
潇洒的马里奥完成签到,获得积分10
4秒前
orixero的应助被snowing采纳,获得10
4秒前
科研通AI6.2的应助被qq大魔王采纳,获得10
4秒前
wanci的应助被今夜无人入眠采纳,获得10
4秒前
kiko的应助被qq大魔王采纳,获得100
4秒前
大模型的应助被故意的忆丹采纳,获得10
5秒前
小蘑菇的应助被姜忆霜采纳,获得10
5秒前
Moving_Dr发布了新的文献求助10
6秒前
五五帅完成签到,获得积分10
6秒前
6秒前
7秒前
8秒前
可可发布了新的文献求助10
9秒前
zhuzhu2025完成签到,获得积分10
9秒前
9秒前
10秒前
风中静白完成签到,获得积分10
10秒前
11秒前
晖晖shining完成签到,获得积分10
11秒前
Ava的应助被晚风将近采纳,获得10
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Energie-Contracting 1500
Klimaschutzrecht durch den Energiesektor im Mehrebenensystem – Ein Rechtsvergleich 1000
Représentation chimique de la structure des kérogènes et des asphaltènes en fonction de leur origine et de leur degré d'évolution 900
Ecotourism 400
Analytical Separation Science 300
Civilization and War 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8069649
求助须知:如何正确求助?哪些是违规求助? 9490406
关于积分的说明 21358638
捐赠科研通 7637809
什么是DOI,文献DOI怎么找? 3398553
关于科研通互助平台的介绍 2528406
邀请新用户注册赠送积分活动 2436534