Yoonhee Shin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yoonhee Shin has a total of 48 co-authors. Here are the top co-authors by number of shared publications:
- Jaewon Jung
Korean Educational Development Institute (KEDI), Jincheon-Gun, South Korea
5 shared publications - Seohyun Choi
Hanyang University, Seoul, Republic of Korea
4 shared publications - Donggil Song
Texas A&M University
3 shared publications - Bokmoon Jung
Korea National University of Education, Cheongju-si, South Korea
2 shared publications Chunju Kim
2 shared publicationsJooyoung Lee
2 shared publications
Latest Publications
- 12 November 2026
- Published by SAGE Publications in Social Science Computer Review
Fine-Tuned Large Language Models for Theory-Aligned Social Science Content Analysis: Evidence From Collaborative Learning Discourse
Theory-based content analysis is central to social science research, but coding context-dependent interactional discourse remains difficult to scale. This study examines whether fine-tuned large language models (LLMs) can support theory-aligned, episode-level coding of complex social interaction, using socially shared metacognitive regulation (SSMR) in collaborative learning discourse as a demanding empirical case. Using a human-coded dataset of 2,372 discourse episodes from undergraduate collaborative problem-solving, we adapted the large language model content analysis (LACA) framework through an AI-aligned codebook, prompt design, and supervised fine-tuning. Prompt-only and fine-tuned models were compared across episode-level classification and multilayer SSMR coding. Fine-tuned models substantially improved agreement with human coding and predictive performance relative to prompt-only baselines. Performance was strongest for episode-level classification and several higher-support coding layers, whereas errors remained concentrated in sparse, boundary-prone, and highly interpretive categories requiring social-intent reconstruction and temporally unfolding context. The findings extend recent work on LLM-assisted qualitative and content analysis by showing both the promise and limits of supervised, theory-aligned automation for multilayer social interaction coding. Overall, the study supports a human-centered approach to LLM-assisted content analysis, in which automated coding can support more stable coding tasks while human expertise remains essential for ambiguous, boundary-prone, and interpretively demanding judgments.
- 12 November 2026
- Published by SAGE Publications in Social Science Computer Review
Fine-Tuned Large Language Models for Theory-Aligned Social Science Content Analysis: Evidence From Collaborative Learning Discourse
Theory-based content analysis is central to social science research, but coding context-dependent interactional discourse remains difficult to scale. This study examines whether fine-tuned large language models (LLMs) can support theory-aligned, episode-level coding of complex social interaction, using socially shared metacognitive regulation (SSMR) in collaborative learning discourse as a demanding empirical case. Using a human-coded dataset of 2,372 discourse episodes from undergraduate collaborative problem-solving, we adapted the large language model content analysis (LACA) framework through an AI-aligned codebook, prompt design, and supervised fine-tuning. Prompt-only and fine-tuned models were compared across episode-level classification and multilayer SSMR coding. Fine-tuned models substantially improved agreement with human coding and predictive performance relative to prompt-only baselines. Performance was strongest for episode-level classification and several higher-support coding layers, whereas errors remained concentrated in sparse, boundary-prone, and highly interpretive categories requiring social-intent reconstruction and temporally unfolding context. The findings extend recent work on LLM-assisted qualitative and content analysis by showing both the promise and limits of supervised, theory-aligned automation for multilayer social interaction coding. Overall, the study supports a human-centered approach to LLM-assisted content analysis, in which automated coding can support more stable coding tasks while human expertise remains essential for ambiguous, boundary-prone, and interpretively demanding judgments.
- 16 June 2026
- Published by Springer Nature in Metacognition and Learning
- Vol. 21 (1) , 29
Capturing the temporal interplay of knowledge construction and group-level regulation in collaborative problem solving
- 16 June 2026
- Published by Springer Nature in Metacognition and Learning
- Vol. 21 (1) , 29
Capturing the temporal interplay of knowledge construction and group-level regulation in collaborative problem solving
- 11 March 2026
- Published by Springer Nature in Education and Information Technologies
- Vol. 31 (10) , 3283-3310
Exploring the relationship between computational thinking behaviors and socially shared metacognitive regulation in collaborative coding across task complexity
- 11 March 2026
- Published by Springer Nature in Education and Information Technologies
- Vol. 31 (10) , 3283-3310
Exploring the relationship between computational thinking behaviors and socially shared metacognitive regulation in collaborative coding across task complexity
- 2 February 2026
- Published by Springer Nature in International Journal of Computer-Supported Collaborative Learning
- Vol. 21 (3) , 503-536
A phase-sensitive multimodal learning analysis of high- and low-performing teams: the dynamics of mutual engagement
- 2 February 2026
- Published by Springer Nature in International Journal of Computer-Supported Collaborative Learning
- Vol. 21 (3) , 503-536
A phase-sensitive multimodal learning analysis of high- and low-performing teams: the dynamics of mutual engagement
- Open Access
- 14 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 87026-87035
Teacher-Student Inter-Brain and Behavioral Synchronies in Remote Education
Interpersonal synchrony plays a crucial role in education. This study investigated inter-brain synchrony (IBS) during remote education and its effects on learning outcomes, rapport, and behavioral synchrony. Twenty-eight participants conducted a vocabulary learning task with a remote teacher under two conditions: voice and webcam conditions. The results showed that participants formed a higher IBS with the remote teacher in the webcam condition. We also observed that the brain regions of frontopolar prefrontal cortex (FP-PFC) and left orbitofrontal cortex (OFC) were positively associated with learning outcomes and rapport, respectively. Furthermore, we observed that the concurrent behavioral synchrony (BS) of eye movements was related to IBS in the left OFC. Our findings provide valuable insights for future research on interpersonal synchrony and their implications for the development of effective teaching methodologies in remote education.
- 14 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 87026-87035
Open AccessTeacher-Student Inter-Brain and Behavioral Synchronies in Remote Education
Interpersonal synchrony plays a crucial role in education. This study investigated inter-brain synchrony (IBS) during remote education and its effects on learning outcomes, rapport, and behavioral synchrony. Twenty-eight participants conducted a vocabulary learning task with a remote teacher under two conditions: voice and webcam conditions. The results showed that participants formed a higher IBS with the remote teacher in the webcam condition. We also observed that the brain regions of frontopolar prefrontal cortex (FP-PFC) and left orbitofrontal cortex (OFC) were positively associated with learning outcomes and rapport, respectively. Furthermore, we observed that the concurrent behavioral synchrony (BS) of eye movements was related to IBS in the left OFC. Our findings provide valuable insights for future research on interpersonal synchrony and their implications for the development of effective teaching methodologies in remote education.
- Open Access
- 5 November 2024
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (6) , 8351-8352
Correction to: The infuence of scafolding for computational thinking on cognitive load and problemsolving skills in collaborative programming
- 5 November 2024
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (6) , 8351-8352
Open AccessCorrection to: The infuence of scafolding for computational thinking on cognitive load and problemsolving skills in collaborative programming
- 16 October 2024
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (1) , 583-606
The influence of scaffolding for computational thinking on cognitive load and problem-solving skills in collaborative programming
- 16 October 2024
- Published by Springer Nature in Education and Information Technologies
- Vol. 30 (1) , 583-606
The influence of scaffolding for computational thinking on cognitive load and problem-solving skills in collaborative programming
- Open Access
- 31 August 2024
- Published by Digital Contents Society in Journal of Digital Contents Society
- Vol. 25 (8) , 2091-2101
Exploring the Role and Design Principles of the Pedagogical Agent: Focusing on a 2D·3D Learning Environment
- 31 August 2024
- Published by Digital Contents Society in Journal of Digital Contents Society
- Vol. 25 (8) , 2091-2101
Open AccessExploring the Role and Design Principles of the Pedagogical Agent: Focusing on a 2D·3D Learning Environment