背景:孤独是一个严重的公共卫生问题。尽管以前的干预措施在减轻孤独感方面取得了一些成功,这个领域正在寻找小说,更有效,和更具可扩展性的解决方案。这里,我们专注于“关系代理”,一种软件代理形式,越来越多地由人工智能和大型语言模型(LLM)提供支持。我们报告了系统综述和荟萃分析,以调查关系主体对各年龄组孤独感的影响。
方法:在本系统综述和荟萃分析中,从成立到2022年9月16日,我们检索了11个数据库,包括OvidMEDLINE和Embase。我们纳入了所有年龄组的随机对照试验和非随机干预研究。这些孤独干预措施,通常试图提高社交技能,社会支持,社交互动,和适应不良的认知。同行评审的期刊文章,书籍,书籍章节,硕士和博士学位论文,或会议文件有资格列入。两名审稿人独立筛选研究,提取的数据,并通过RoB2和ROBINS-I工具评估偏倚风险。我们在随机效应荟萃分析中计算了Hedge的汇总估计值,并进行了敏感性和亚组分析。我们通过漏斗图评估了出版偏差,Egger\'stest,和修剪和填充算法。
结果:我们的搜索确定了3,935条记录,其中14条符合资格标准,并被纳入我们的荟萃分析。纳入的研究包括286名参与者,个人研究样本量从4到42名参与者(x²=20.43,s=11.58,x²=20)。我们使用了Bonferroni校正,αBonferroni=0.05/4=0.0125,并应用了Knapp-Hartung调整。关联剂在调整后的αBonferroni上显着降低了孤独感(g=-0.552;95%Knapp-HartungCI,-0.877至-0.226;P=0.003),这相当于孤独的适度减少。
结论:我们的研究结果是目前同类研究中最全面的,为相关药物的疗效提供了有希望的证据。关系代理是一种有前途的技术,可以以可扩展的方式减轻孤独,并且可以成为其他方法的有意义的补充。LLM的出现应该提高它们的功效,需要进一步的研究来探索关系代理的优化设计和使用。未来的研究还可以解决当前结果的缺点,如样本量小,偏倚风险高。特别是年轻观众在过去的研究中被忽视了。
BACKGROUND: Loneliness is a serious public health concern. Although previous interventions have had some success in mitigating loneliness, the field is in search of novel, more effective, and more scalable solutions. Here, we focus on \"relational agents\", a form of software agents that are increasingly powered by artificial intelligence and large language models (LLMs). We report on a systematic review and meta-analysis to investigate the impact of relational agents on loneliness across age groups.
METHODS: In this systematic review and meta-analysis, we searched 11 databases including Ovid MEDLINE and Embase from inception to Sep 16, 2022. We included randomised controlled trials and non-randomised studies of interventions published in English across all age groups. These loneliness interventions, typically attempt to improve social skills, social support, social interaction, and maladaptive cognitions. Peer-reviewed journal articles, books, book chapters, Master\'s and PhD theses, or conference papers were eligible for inclusion. Two reviewers independently screened studies, extracted data, and assessed risk of bias via the RoB 2 and ROBINS-I tools. We calculated pooled estimates of Hedge\'s g in a random-effects meta-analysis and conducted sensitivity and sub-group analyses. We evaluated publication bias via funnel plots, Egger\'s test, and a trim-and-fill algorithm.
RESULTS: Our search identified 3,935 records of which 14 met eligibility criteria and were included in our meta-analysis. Included studies comprised 286 participants with individual study sample sizes ranging from 4 to 42 participants (x̄ = 20.43, s = 11.58, x̃ = 20). We used a Bonferroni correction with αBonferroni = 0.05 / 4 = 0.0125 and applied Knapp-Hartung adjustments. Relational agents reduced loneliness significantly at an adjusted αBonferroni (g = -0.552; 95% Knapp-Hartung CI, -0.877 to -0.226; P = 0.003), which corresponds to a moderate reduction in loneliness.
CONCLUSIONS: Our results are currently the most comprehensive of their kind and provide promising evidence for the efficacy of relational agents. Relational agents are a promising technology that can alleviate loneliness in a scalable way and that can be a meaningful complement to other approaches. The advent of LLMs should boost their efficacy, and further research is needed to explore the optimal design and use of relational agents. Future research could also address shortcomings of current results, such as small sample sizes and high risk of bias. Particularly young audiences have been overlooked in past research.