{"resourceId":"ijethe-question-chain-prompting-genai-self-regulated-learning-quasi-experiment-guangzhou-20261023","versions":[{"version":"external-8cba347fef78224875f090718374e7c29e1374043f0c5722d5a0677da7bc5866","resource":{"id":"ijethe-question-chain-prompting-genai-self-regulated-learning-quasi-experiment-guangzhou-20261023","title":"Question-chain prompting for generative AI raised self-regulated learning behaviours, metacognitive awareness and course achievement versus free-form use in an 83-student quasi-experiment","organization":"South China Normal University, Lehigh University and Guangzhou University (study authors)","sector":"Higher education guided student use of generative AI for coursework","geography":"Guangzhou, China (transferability to US institutions untested)","publishedAt":"International Journal of Educational Technology in Higher Education, volume 23, article 57, published 23 October 2026","publicationDate":"2026-10-23","eventDate":null,"sourceName":"International Journal of Educational Technology in Higher Education (Springer Nature)","sourceLabel":"Peer-reviewed open-access journal article","sourceUrl":"https://link.springer.com/article/10.1186/s41239-026-00632-7","evidenceClass":"academic-research","outcomeClass":"emerging","topics":["knowledge-work","operating-model"],"finding":"A quasi-experiment with 83 undergraduates in three intact classes of a television programme production course at a university in Guangzhou tested question-chain prompting during a GenAI-supported short-film project using DeepSeek. The control class (n=28) used free-form questioning; two classes used progressive (n=30) or divergent (n=25) question chains, an instructional package of specific, sequenced and required questions. Using interaction logs, reflections, an adapted metacognitive awareness inventory and course grades, both question-chain groups showed significantly more learning-strategy and learning-monitoring behaviours than the control and scored significantly higher on knowledge of cognition, regulation of cognition and academic achievement. The two chain types did not differ. The authors caution that reflection prompts differed by condition and that effects reflect the whole package rather than chaining alone.","sledRelevance":"Offers a low-cost instructional design (structured prompting sequences) that institutions could test to counter passive AI use, a recurring student-success concern.","evidence":"Peer-reviewed quasi-experiment with log coding, a validated-but-adapted instrument and grades; non-random assignment by intact class.","architectureImplications":"Tool-agnostic: the intervention is an instruction sheet that structures questions, not a product change. Interpretation: it could be built into course templates or assistant system prompts.","governanceImplications":"Suggests course-level AI guidance could specify how students question AI, not only whether they may use it.","securityPrivacyImplications":"Study used interaction logs for coding; institutions replicating this need consent and log-handling rules.","caveats":"Single instructor, single course, intact classes, Chinese context and DeepSeek; adapted 10-item instrument; differing reflection prompts.","streamIds":["student-success"],"roles":{"sales":"Sales framing: this study gives evidence that how students question AI matters as much as access. Use it to ask teaching centres whether AI guidance tells students how to engage, not just whether they may. A bounded engagement could build question-chain templates for a few project-based courses and measure engagement and grades. Do not claim the method will raise achievement everywhere; it comes from one instructor's classes in China with non-random assignment.","engineering":"Engineering framing: the intervention is tool-agnostic, a sequenced set of required questions given to students, so it can be delivered through instruction sheets, LMS templates or an assistant's system prompt. Validate by coding interaction logs for planning and monitoring behaviour and by comparing grades against a free-form control. Note that log collection needs consent and retention rules, and that results came from DeepSeek in a single course.","delivery":"Delivery framing: delivery would package question chains as course-level guidance for AI-supported projects. Work with one or two instructors to write chains tied to assignment stages, run a comparison section using free-form use, and gather logs, reflections and grades. Keep reflection prompts identical across groups to avoid the study's confound, and review results with the teaching centre before adding chains to institution-wide AI literacy materials."},"roleDetails":{"sales":{"customerProblem":"Students use generative AI passively, weakening self-regulated learning in project-based courses.","stakeholders":["Center for teaching and learning","Instructional designers","Academic affairs AI working group","Course instructors"],"discoveryQuestions":["Does course AI guidance say how students should question AI?","Which project-based courses rely heavily on AI use?","Can interaction logs be collected with consent?"],"valueHypothesis":"Interpretation: structured question sequences can make student AI use more active and may improve metacognition and grades.","potentialEngagement":"A one-term pilot writing question-chain templates for two project-based courses, with a free-form comparison section.","unsupportedClaims":["That gains transfer to US institutions","That chaining alone, without the package, drives effects","Any retention effect"]},"engineering":{"fit":"Any course where students already use a general-purpose AI assistant for project work.","architectureIntegration":"Instruction sheets, LMS templates or assistant system prompts that require sequenced questions.","prerequisites":["Assignment stages mapped to question chains","Consent process for log collection","Comparison section"],"constraints":["Single course and instructor","Chinese context and DeepSeek","Adapted instrument"],"security":"Collect interaction logs only with consent, de-identify for analysis and set retention limits.","proofOfValue":["Code logs for planning and monitoring behaviours","Compare grades with a free-form control","Use identical reflection prompts across groups"]},"delivery":{"work":"Design, run and evaluate question-chain guidance for AI-supported course projects.","dependencies":["Instructor participation","Teaching-centre design support","Log access"],"ownership":"Center for teaching and learning with participating instructors.","skillsAdoption":"Instructors learn to write question chains; students practise structured questioning as part of AI literacy.","governanceCheckpoints":["Consent and log-retention approval","Mid-project review of log quality","End-of-term review before broader rollout"],"acceptanceCriteria":["Proposed: chain groups show more monitoring behaviours in coded logs than the control","Proposed: grade comparison reported with design limits","Proposed: identical reflection prompts used across groups"],"risks":["Confounding by class or instructor","Student resistance to required prompts","Over-generalizing from one course"]}},"retrievedAt":"2026-10-25T03:21:20Z","enrichedAt":"2026-10-25T03:25:36Z","enrichmentBasis":"retrieved source","accessibilityWorkforceImplications":"Structured prompts may help students with less AI experience, but this was not tested by subgroup.","procurementImplications":"None directly; the intervention needs no new purchase.","operatingModelImplications":"Faculty development could teach question-chain design as part of AI literacy, with teaching centres providing templates.","sourceVerification":{"openedUrl":"https://link.springer.com/article/10.1186/s41239-026-00632-7","referenceExcerpt":"both experimental groups scored significantly higher than the control group on knowledge of cognition, regulation of cognition, and academic achievement.","promptVersion":"sled-research-v4.0","model":null,"basis":"agent-reported inspection"}}}]}