Collaborative AI-in-the-loop pedagogical conversational agent to enhance social and cognitive presence in cMOOC

IF 10.5 1区教育学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers & Education Pub Date : 2025-09-05 DOI:10.1016/j.compedu.2025.105451

Jianjun Xiao , Yulin Tian , Cixiao Wang

{"title":"Collaborative AI-in-the-loop pedagogical conversational agent to enhance social and cognitive presence in cMOOC","authors":"Jianjun Xiao , Yulin Tian , Cixiao Wang","doi":"10.1016/j.compedu.2025.105451","DOIUrl":null,"url":null,"abstract":"<div><div>While connectivist MOOCs (cMOOCs) emphasize learner autonomy and peer interaction, the lack of structured facilitation often hinders the development of social and cognitive presence. This study investigates how Pedagogical Conversational Agents (PCAs) enhance learners' social and cognitive presence in cMOOC environments. Using a within-subjects quasi-experimental design, 344 learners (primarily in-service teachers, 93.60 %) participated in a cMOOC course over four weeks. The 54 discussion topics generated by learners were randomly assigned to experimental (with-PCA, <em>N</em> = 19) and control (without-PCA, <em>N</em> = 35) conditions. A collaborative AI-in-the-loop design was implemented where AI-generated content underwent human review before publication. Analysis of 5301 discussion posts using the Community of Inquiry framework revealed that PCAs significantly enhanced open communication (<em>p < .001, r=-0.213</em>) and group cohesion (<em>p=.027, r=-0.106</em>) in social presence, while improving higher-order cognitive processes, including integration (<em>p=.011, r=-0.119</em>) and resolution (<em>p=.028, r=-0.145</em>). Direct interaction with PCAs yielded superior outcomes in affective expression (<em>p=.027, r=0.103</em>) and specific communication behaviors compared to co-present modes. The findings demonstrate that PCAs provide compensatory support by strengthening cMOOCs' relatively weak components of cognitive presence (integration and resolution) rather than providing comprehensive intervention; direct interaction modes with PCA yield more benefit for deep exploration and social engagement. This offers evidence-based design strategies for AI agent implementation in online education.</div></div>","PeriodicalId":10568,"journal":{"name":"Computers & Education","volume":"240 ","pages":"Article 105451"},"PeriodicalIF":10.5000,"publicationDate":"2025-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computers & Education","FirstCategoryId":"95","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0360131525002192","RegionNum":1,"RegionCategory":"教育学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}

引用次数: 0

Abstract

While connectivist MOOCs (cMOOCs) emphasize learner autonomy and peer interaction, the lack of structured facilitation often hinders the development of social and cognitive presence. This study investigates how Pedagogical Conversational Agents (PCAs) enhance learners' social and cognitive presence in cMOOC environments. Using a within-subjects quasi-experimental design, 344 learners (primarily in-service teachers, 93.60 %) participated in a cMOOC course over four weeks. The 54 discussion topics generated by learners were randomly assigned to experimental (with-PCA, N = 19) and control (without-PCA, N = 35) conditions. A collaborative AI-in-the-loop design was implemented where AI-generated content underwent human review before publication. Analysis of 5301 discussion posts using the Community of Inquiry framework revealed that PCAs significantly enhanced open communication (p < .001, r=-0.213) and group cohesion (p=.027, r=-0.106) in social presence, while improving higher-order cognitive processes, including integration (p=.011, r=-0.119) and resolution (p=.028, r=-0.145). Direct interaction with PCAs yielded superior outcomes in affective expression (p=.027, r=0.103) and specific communication behaviors compared to co-present modes. The findings demonstrate that PCAs provide compensatory support by strengthening cMOOCs' relatively weak components of cognitive presence (integration and resolution) rather than providing comprehensive intervention; direct interaction modes with PCA yield more benefit for deep exploration and social engagement. This offers evidence-based design strategies for AI agent implementation in online education.

查看原文本刊更多论文

协作式ai -in- loop教学会话代理在cMOOC中增强社会和认知存在

虽然连接主义mooc （cMOOCs）强调学习者的自主性和同伴互动，但缺乏结构化的促进往往阻碍了社会和认知存在的发展。本研究探讨教学会话代理（PCAs）如何在cMOOC环境中增强学习者的社会和认知存在。采用主题内准实验设计，344名学习者（主要是在职教师，占93.60%）参加了为期四周的cMOOC课程。学习者产生的54个讨论话题被随机分配到实验（含pca， N = 19）和控制（不含pca， N = 35）两组。人工智能生成的内容在发布前经过人工审查，实现了人工智能在循环中的协作设计。使用探究社区框架对5301篇讨论帖子进行的分析显示，pca显著增强了社会存在中的开放沟通（p < 0.001, r=-0.213）和群体凝聚力（p= 0.027, r=-0.106），同时改善了高阶认知过程，包括整合（p= 0.011, r=-0.119）和解决（p= 0.028, r=-0.145）。与共同在场模式相比，与pca直接互动在情感表达（p= 0.027, r=0.103）和特定沟通行为方面产生了更好的结果。研究结果表明，pca通过强化cMOOCs相对较弱的认知存在成分（整合和解决）来提供补偿性支持，而不是提供综合干预；与PCA的直接交互模式更有利于深度探索和社会参与。这为在线教育中人工智能代理的实现提供了基于证据的设计策略。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Computers & Education 工程技术-计算机：跨学科应用

CiteScore

27.10

自引率

5.80%

发文量

204

审稿时长

42 days

期刊介绍： Computers & Education seeks to advance understanding of how digital technology can improve education by publishing high-quality research that expands both theory and practice. The journal welcomes research papers exploring the pedagogical applications of digital technology, with a focus broad enough to appeal to the wider education community.