Jiacheng Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiacheng Zhao has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Donald Scott McCrickard
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA
4 shared publications - Jixiang Fan
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA
4 shared publications - Michael Bolmer
Virginia Tech,Department of Computer Science,Blacksburg,VA,USA
3 shared publications - Sunggyeol Oh
Department of Computer Science, Virginia Tech, Blacksburg, Virginia, USA
3 shared publications - Carson Russo
Virginia Tech,Department of Computer Science,Blacksburg,VA,USA
2 shared publications - Wei-Lu Wang
Department of Computer Science, Virginia Tech, Blacksburg, VA, USA
2 shared publications
Latest Publications
- Open Access
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Unpacking Empathy Development in HCI Learners: Patterns from Diary Reflections and Peer Discussions
- 13 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-5
Open AccessUnpacking Empathy Development in HCI Learners: Patterns from Diary Reflections and Peer Discussions
- Open Access
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1327-1328
Diary Study for Fostering Collaboration and Student Voice
- 17 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 1327-1328
Open AccessDiary Study for Fostering Collaboration and Student Voice
- 2 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Optimizing Diary Studies Learning Outcomes with Fine-Tuned Large Language Models on the Diaryquest Platform
This innovative practice full paper describes how the fine-tuned large language model (LLM) enhances student reflection and faculty efficiency in an introductory Human-Computer Interaction (HCI) course through AI-generated personalized feedback and practical data analysis. In HCI education, traditional diary studies provide a way to extract unique insights from user experiences. However, instructors, especially in large classes, often face resource limitations that impede a thorough analysis of diary entries, preventing students from receiving personalized feedback. Using a Mistral 7B model fine-tuned with more than 1,000 diary entries, the platform provides constructive feedback tailored to individual student submissions. In addition, the platform employs advanced data analytics and visualization techniques, including semantic search, thematic analysis, and semantic graphs, enabling faculty to navigate and review large volumes of student diary entries efficiently. The survey results revealed that fine-tuned LLM-generated feedback provides high-quality feedback and significantly enhances the depth of student reflections. At the same time, the AI data analytics tool improves faculty efficiency in teaching and assessment. This study highlights the potential of using LLMs to bridge the gap between a large-scale student writing dataset and human-centered learning technologies, suggesting future research on AI-based teaching environments.
- 2 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-9
Optimizing Diary Studies Learning Outcomes with Fine-Tuned Large Language Models on the Diaryquest Platform
This innovative practice full paper describes how the fine-tuned large language model (LLM) enhances student reflection and faculty efficiency in an introductory Human-Computer Interaction (HCI) course through AI-generated personalized feedback and practical data analysis. In HCI education, traditional diary studies provide a way to extract unique insights from user experiences. However, instructors, especially in large classes, often face resource limitations that impede a thorough analysis of diary entries, preventing students from receiving personalized feedback. Using a Mistral 7B model fine-tuned with more than 1,000 diary entries, the platform provides constructive feedback tailored to individual student submissions. In addition, the platform employs advanced data analytics and visualization techniques, including semantic search, thematic analysis, and semantic graphs, enabling faculty to navigate and review large volumes of student diary entries efficiently. The survey results revealed that fine-tuned LLM-generated feedback provides high-quality feedback and significantly enhances the depth of student reflections. At the same time, the AI data analytics tool improves faculty efficiency in teaching and assessment. This study highlights the potential of using LLMs to bridge the gap between a large-scale student writing dataset and human-centered learning technologies, suggesting future research on AI-based teaching environments.
- Open Access
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 244-248
Structuring Collaborative Reflection: Integrating Diary Study and Focus Group Discussion
- 17 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 244-248
Open AccessStructuring Collaborative Reflection: Integrating Diary Study and Focus Group Discussion
- Open Access
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Boosting Diary Study Outcomes with a Fine-Tuned Large Language Model
- 25 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessBoosting Diary Study Outcomes with a Fine-Tuned Large Language Model
- Open Access
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1765
DiaryQuest: A Web-Based Learning System Utilizing Diary Study
Diary studies are pivotal in enhancing student reflection and deepening understanding of subjects such as Human-Computer Interaction (HCI). However, traditional methods of diary entry analysis are time-consuming and labor-intensive. Based on Jixiang Fan's four-phase diary study model, we designed and implemented the new learning management system -- DiaryQuest. DiaryQuest is a web-based learning management system designed to address challenges in implementing diary studies within educational settings, especially in large classroom environments. It offers a streamlined approach by providing tools for educators to create diary assignments, track student submissions, and analyze entries using advanced methods like Latent Dirichlet Allocation (LDA) and sentiment analysis. For students, it features an intuitive interface that includes progress tracking to ensure consistent and timely diary entries. The platform also incorporates interactive visualizations, such as word clouds and dynamic analytics tables, which allow educators to delve deeper into student insights and observations. These features make DiaryQuest an effective tool for managing diary studies, increasing engagement, and fostering a personalized and reflective learning experience. By simplifying the management and analysis of diary studies, DiaryQuest promotes a more interactive and productive educational environment, enabling students and educators to understand the learning material and each other better. This innovation enhances educational outcomes and prepares students with critical skills in data analysis and reflective thinking, which are essential for the HCI field.
- 18 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 1765
Open AccessDiaryQuest: A Web-Based Learning System Utilizing Diary Study
Diary studies are pivotal in enhancing student reflection and deepening understanding of subjects such as Human-Computer Interaction (HCI). However, traditional methods of diary entry analysis are time-consuming and labor-intensive. Based on Jixiang Fan's four-phase diary study model, we designed and implemented the new learning management system -- DiaryQuest. DiaryQuest is a web-based learning management system designed to address challenges in implementing diary studies within educational settings, especially in large classroom environments. It offers a streamlined approach by providing tools for educators to create diary assignments, track student submissions, and analyze entries using advanced methods like Latent Dirichlet Allocation (LDA) and sentiment analysis. For students, it features an intuitive interface that includes progress tracking to ensure consistent and timely diary entries. The platform also incorporates interactive visualizations, such as word clouds and dynamic analytics tables, which allow educators to delve deeper into student insights and observations. These features make DiaryQuest an effective tool for managing diary studies, increasing engagement, and fostering a personalized and reflective learning experience. By simplifying the management and analysis of diary studies, DiaryQuest promotes a more interactive and productive educational environment, enabling students and educators to understand the learning material and each other better. This innovation enhances educational outcomes and prepares students with critical skills in data analysis and reflective thinking, which are essential for the HCI field.