Skip to content
DraconiticResearch
Search Sources API
194,164 studies31 sourcesUpdated 1 h ago
Peer-reviewedCC BY 4.0PLOS One

What students ask matters: Static and longitudinal questioning patterns in student–LLM dialogue and self-reported cognitive engagement

  • Jingru Qu1
  • Ling Dai2
  • Mengjie Yin
  1. 1School of Humanities and Social Science, the Chinese University of Hong Kong, Shenzhen, China
  2. 2Institute of Education, Nanjing University, Nanjing, China
Open at sourceDOICite

Abstract

This study examines students’ questioning as an interaction mechanism in student–LLM philosophical dialogue and how it relates to self-reported critical thinking (CT) and creative thinking (CrT) engagement. Participants were 106 first-year postgraduate students in a Chinese university general education course who completed an end-of-semester assignment using an institutional ChatGPT model embedded in the learning platform. Student questions in dialogue transcripts were coded into six categories aligned with the revised Bloom’s taxonomy. We then applied latent profile analysis (LPA) to identify static questioning profiles and group-based trajectory modeling (GBTM) to capture longitudinal development across conversation rounds, followed by subgroup comparisons on perceived CT and CrT. LPA yielded three profiles: Fact-focused, Explanation-focused, and Evaluation-focused Questioners. GBTM revealed two trajectories with a key divergence around Rounds 5–7: some students plateaued at application and analytical questioning, while others progressed toward evaluative and exploratory questioning. Fact-focused Questioners reported lower CT and CrT engagement scores; plateauing trajectories reported lower CT. Findings highlight how questioning patterns are associated with differential self-reported cognitive engagement in student–LLM dialogue and inform scaffold design to promote higher-order inquiry.

Related

  1. Longitudinal patterns of digital parenting restrictions and adolescent screen use: Insights from the Adolescent Brain Cognitive Development (ABCD) study
    Daniel Lopez, Arturo Lopez-Flores, Gloria Ruiz-Orozco +1
    PLOS Digital HealthPeer-reviewedCC BYFull textGeneral biologyEpidemiology & public healthPLOSEurope PMCPMC
  2. Maintaining cognitive gains in type 2 diabetes: Barriers, supports, and patterns of strategy use
    Heather E. Cuevas, Jeeyeon Kim, Shenell T. Wood
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceEndocrinology & metabolismPLOS
  3. Marital status and incident screen-positive cognitive impairment in a Taiwanese longitudinal cohort (2005–2016): Associations vary by cognitive screening instrument
    Yi-Chao Zhou, Yi-Chang Chou, Yin-Ling Hung +1
    PLOS OnePeer-reviewedCC BY 4.0Full textNeuroscienceCardiovascular medicinePLOS
  4. Hippocampal-somatomotor coactivation and perceived benefit following Mindfulness-Based Cognitive Therapy for Life in healthcare students: An exploratory randomized study
    N. Clairis, L. F. Saccaro, S. Delplanque +9
    bioRxivPreprintCC BY-NCFull textNeurosciencebioRxiv
  5. Cerebral Artery Stenosis, Glymphatic Dysfunction, and Cognitive Trajectories: A Longitudinal Cohort Study of Community-Dwelling Older Adults.
    Weizhuang Yuan, Xingyang Niu, Linfang Lan +1
    CNS neuroscience & therapeuticsPeer-reviewedCC BYFull textNeuroscienceEurope PMC

Cite

BibTeXRIS
BibTeX
@article{qu2026what,
  title = {{What students ask matters: Static and longitudinal questioning patterns in student–LLM dialogue and self-reported cognitive engagement}},
  author = {Jingru Qu and Ling Dai and Mengjie Yin},
  journal = {PLOS One},
  year = {2026},
  month = sep,
  doi = {10.1371/journal.pone.0356183},
  url = {https://doi.org/10.1371/journal.pone.0356183},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - What students ask matters: Static and longitudinal questioning patterns in student–LLM dialogue and self-reported cognitive engagement
AU  - Jingru Qu
AU  - Ling Dai
AU  - Mengjie Yin
PY  - 2026
DA  - 2026/09/08
JO  - PLOS One
DO  - 10.1371/journal.pone.0356183
UR  - https://doi.org/10.1371/journal.pone.0356183
AB  - This study examines students’ questioning as an interaction mechanism in student–LLM philosophical dialogue and how it relates to self-reported critical thinking (CT) and creative thinking (CrT) engagement. Participants were 106 first-year postgraduate students in a Chinese university general education course who completed an end-of-semester assignment using an institutional ChatGPT model embedded in the learning platform. Student questions in dialogue transcripts were coded into six categories aligned with the revised Bloom’s taxonomy. We then applied latent profile analysis (LPA) to identify static questioning profiles and group-based trajectory modeling (GBTM) to capture longitudinal development across conversation rounds, followed by subgroup comparisons on perceived CT and CrT. LPA yielded three profiles: Fact-focused, Explanation-focused, and Evaluation-focused Questioners. GBTM revealed two trajectories with a key divergence around Rounds 5–7: some students plateaued at application and analytical questioning, while others progressed toward evaluative and exploratory questioning. Fact-focused Questioners reported lower CT and CrT engagement scores; plateauing trajectories reported lower CT. Findings highlight how questioning patterns are associated with differential self-reported cognitive engagement in student–LLM dialogue and inform scaffold design to promote higher-order inquiry.
SN  - 1932-6203
ER  -