Dr BA, Shen    巴深 博士
Assistant Professor
Department of Curriculum and Instruction
Contact
ORCiD
0000-0001-6535-8335
Phone
(852) 2948 7793
Fax
(852) 2948 7563
Email
bas@eduhk.hk
Address
10 Lo Ping Road, Tai Po, New Territories, Hong Kong
Website
https://pappl.eduhk.hk/rich/web/person.xhtml?pid=305664&name=BA, Shen
Scopus ID
57194497142
SDGs
4 - Quality Education
5 - Gender Equality
9 - Industry, Innovation and Infrastructure
10 - Reduced Inequality
Research Interests
Dr. Ba's research interests are under the theme "Artificial Intelligence and Learning Analytics in Collaborative Inquiry (ALIC)", which include:
  • Analyzing multimodal data (e.g., text, speech, gestures, and visual artifacts) through advanced learning analytics techniques to understand, assess, and optimize the processes of collaborative inquiry;
  • Fostering effective collaborative learning environments using the Community of Inquiry framework, emphasizing cognitive, social, and teaching presences, and incorporating data-driven insights to enhance assessment and feedback practices;
  • Integrating artificial intelligence to support and enhance collaborative inquiry by enabling real-time assessment, personalized feedback, adaptive scaffolding, and deeper analysis of group dynamics;
  • Combining quantitative ethnography with multimodal data to assess and model complex learning and social interactions, generating actionable feedback to improve both individual and group performance;
  • Designing innovative assessment and feedback mechanisms that leverage AI and multimodal data to provide timely, formative feedback, promote self-regulation, and support meaningful learning outcomes in collaborative settings;
External Appointments

Academic Journals:

  • Editorial Board Member, Computers & Education
  • Early Career Researcher Editorial Board Member, British Journal of Educational Technology


Academic Organizations:

  • Council Member, Society of International Chinese in Education Technology
Personal Profile

Dr. Ba is an Assistant Professor in the Department of Curriculum and Instruction at The Education University of Hong Kong (EdUHK). He earned his Ph.D. in Educational Technology from Central China Normal University and was a visiting scholar in the Department of Educational Studies at The Ohio State University during his doctoral studies. Before joining EdUHK, he served as a Postdoctoral Fellow and Part-Time Lecturer in the Faculty of Education at The University of Hong Kong (HKU).


Dr. Ba’s research focuses on the intersection of education and information technology, with an emphasis on advancing online and blended learning environments. He leverages artificial intelligence (AI) and learning analytics to analyze multimodal data, such as text, speech, gestures, and interaction logs, to gain deeper insights into cognitive, emotional, and social processes in collaborative learning. By integrating the Community of Inquiry framework with innovative methodologies like quantitative ethnography, his work seeks to enhance collaborative inquiry, enabling learners to co-construct knowledge while fostering meaningful learning experiences. A significant aspect of his research includes designing AI-driven systems for developmental learning assessment and personalized feedback, creating dynamic, real-time mechanisms to support self-regulated learning and improve group engagement.


With a strong interdisciplinary focus, Dr. Ba bridges educational technologies, data analytics, and pedagogy to address critical challenges in modern education. His work contributes to the development of transformative approaches for understanding and improving how learners interact, collaborate, and grow in digital learning environments.


Research Projects (as Principal Investigator):

  • Early Career Scheme (2026–2028): "From analytics to actions: Enhancing feedback practices in inquiry-based discussion through prescriptive network analytics," funded with HK$942,000.
  • EdUHK x HKUST Joint Centre for Artificial Intelligence (2025–2027): "Harnessing multi-agent simulations to enhance university students’ collaborative inquiry skills," funded with HK$484,652.
  • Additional Funding Resources for Scholarship of Teaching and Learning Projects (2024–2026): "Leveraging Generative Artificial Intelligence to Scaffold Collaborative Inquiry Based on Learning Analytics Insights," funded with HK$800,000.
  • Teaching Development Grant (2024–2025): "Enhancing formative assessment and feedback in collaborative inquiries with an AI-powered analytical module," funded with HK$400,000.
  • Start-up Research Grant (2024–2025): "Exploring the usage and effectiveness of GAI in university students’ inquiry-based learning," funded with HK$199,993.


Dr. Ba is actively seeking motivated Ph.D. and EdD students, as well as research assistants, to join his team and collaborate on cutting-edge research in these areas (last updated on June 30, 2025).

Research Interests
Dr. Ba's research interests are under the theme "Artificial Intelligence and Learning Analytics in Collaborative Inquiry (ALIC)", which include:
  • Analyzing multimodal data (e.g., text, speech, gestures, and visual artifacts) through advanced learning analytics techniques to understand, assess, and optimize the processes of collaborative inquiry;
  • Fostering effective collaborative learning environments using the Community of Inquiry framework, emphasizing cognitive, social, and teaching presences, and incorporating data-driven insights to enhance assessment and feedback practices;
  • Integrating artificial intelligence to support and enhance collaborative inquiry by enabling real-time assessment, personalized feedback, adaptive scaffolding, and deeper analysis of group dynamics;
  • Combining quantitative ethnography with multimodal data to assess and model complex learning and social interactions, generating actionable feedback to improve both individual and group performance;
  • Designing innovative assessment and feedback mechanisms that leverage AI and multimodal data to provide timely, formative feedback, promote self-regulation, and support meaningful learning outcomes in collaborative settings;
External Appointments

Academic Journals:

  • Editorial Board Member, Computers & Education
  • Early Career Researcher Editorial Board Member, British Journal of Educational Technology


Academic Organizations:

  • Council Member, Society of International Chinese in Education Technology
Career Overview
Global Institute for Emerging Technologies
Funding Member
Date : 12/2024- Present
The Education University of Hong Kong
Assistant Professor
Date : 08/2023- Present
The University of Hong Kong
Postdoctoral Fellow
Date : 01/2022-08/2023
The University of Hong Kong
Lecturer (PT)
Date : 01/2022-08/2023
Ohio State University
Visiting Scholar
Date : 09/2019-08/2020
Department of Education of Hubei Province
System Designer (PT)
Date : 01/2019-06/2019
Projects
From analytics to actions: Enhancing feedback practices in inquiry-based discussion through prescriptive network analytics
As the demand for cultivating students' higher-order thinking (HOT) intensifies in higher education, inquiry-based discussion (IBD) has emerged as a widely adopted pedagogical approach across disciplines. However, despite its potential to foster critical, reflective, and interactive discourse, the effectiveness of IBD is not guaranteed, as the quality of instructor feedback significantly influences how students understand and navigate the complex IBD process. Due to time and resource constraints, instructors face difficulties in monitoring student discussions and providing timely, actionable, and personalized feedback. While learning analytics (LA) offer promising solutions to provide instructors with fine-grained insights into IBD, their adoption in practice remains limited due to the data science expertise required. Consequently, many instructors miss the opportunity to leverage LA advancements, hindering their ability to provide quality feedback, which in turn limits students’ engagement and development in IBD.

Grounded in the community of inquiry (CoI) model, this project strives to bridge the gap between advanced LA and practical solutions that enhance instructors’ feedback practices. Specifically, the project aims to: (1) develop a prescriptive network analytics (PNA) tool tailored for IBD feedback practices; (2) enhance instructor feedback practices with transparent analytics, interpretable insights, and adaptive recommendations; (3) improve student IBD engagement and outcomes through timely, actionable, and personalized feedback; and (4) establish a comprehensive IBD feedback framework integrating theoretical principles, analytical insights, and effective practices.This project will unfold in three phases. In phase 1, an exploratory study involving 25 instructors and 350 students will be conducted using surveys and interviews to identify specific needs for LA-assisted feedback. A prototype PNA tool will be developed following this phase. Phase 2 will employ a design-based research approach to iteratively design, implement, analyze, and refine the prototype through collaboration with four instructors in real-world educational settings. In phase 3, a quasi-experiment will be conducted with six instructors and their respective classes (240 to 360 students in total) to evaluate the effectiveness of PNA-assisted feedback practices. Quantitative, qualitative, and computational data will be collected and analyzed across phases 2 and 3.

The significance of this project extends beyond the development of a single tool. By making theory-informed analytics more accessible and actionable for practitioners, the project aims to transform feedback practices in IBD, ultimately contributing to the more effective development of HOT in higher education.
Project Start Year: 2026, Principal Investigator(s): BA, Shen
SDGs Information: 4 - Quality Education, 5 - Gender Equality, 9 - Industry, Innovation and Infrastructure, 10 - Reduced Inequality
 
Harnessing Multi-agent Simulations to Enhance University Students’ Collaborative Inquiry Skills
This project aims to enhance collaborative inquiry - a critical 21st-century skill - by addressing key gaps in higher education, such as the overemphasis on group outcomes, inflexible group dynamics, and limited scalable tools for assessment and improvement. To tackle these challenges, the project develops a multi-agent simulation (MAS) system powered by large language models (LLMs) to provide university students with dynamic, adaptive, and scalable environments for practicing and refining collaborative inquiry skills. The project has three primary objectives: (1) to design and develop the MAS tool, enabling students to interact with simulated agents that replicate diverse roles and problem-solving strategies, offering tailored opportunities to enhance collaboration; (2) to optimize the tool by examining the effects of agent configurations, task structures, and feedback mechanisms on learning processes and skill development; and (3) to implement and validate the MAS system in real educational contexts through mixed-methods research to assess its effectiveness and adaptability. Conducted in two phases—iterative development via pilot studies and large-scale implementation—the project employs design-based research (DBR) for iterative refinement, leveraging learning analytics to analyze collaborative processes. Theoretically, it advances understanding of collaborative inquiry by bridging individual skill development and group dynamics, aligning with and expanding the Community of Inquiry framework. Practically, the MAS system offers a scalable, adaptable solution to foster engagement, promote diverse interactions, and improve both collaborative processes and learning outcomes in higher education.
Project Start Year: 2025, Principal Investigator(s): BA, Shen
SDGs Information: 4 - Quality Education, 5 - Gender Equality, 9 - Industry, Innovation and Infrastructure, 10 - Reduced Inequality
 
Leveraging Generative Artificial Intelligence to Scaffold Collaborative Inquiry Based on Learning Analytics Insights
This project aims to advance the theoretical, methodological, and practical understanding of generative artificial intelligence (GAI) scaffolding in collaborative inquiry (CI). Theoretically, it will propose an updated framework that incorporates the roles and influence of GAI in CI, addressing gaps in traditional CI frameworks which focus solely on human interactions. Methodologically, the project will develop a system that integrates GAI scaffolding to analyze CI dynamics, leveraging human-GAI and human-human interactions to track cognitive, metacognitive, and other skill developments more comprehensively than traditional measures. Practically, the project will evaluate the effectiveness of GAI scaffolding on CI processes and outcomes through experimental studies, identifying best practices and providing insights into how GAI impacts skill development and reshapes CI in the GAI era.
Project Start Year: 2024, Principal Investigator(s): BA, Shen
SDGs Information: 4 - Quality Education, 10 - Reduced Inequality
 
Enhancing formative assessment and feedback in collaborative inquiries with an AI-powered analytical module
Collaborative inquiry is one of the most prevalent learning approaches in higher education. It involves students working together through sustained communication to solve problems and construct knowledge. Formative assessment and feedback are vital for developing students’ higher-order thinking skills, especially problem-solving and critical thinking, within collaborative inquiries. However, university instructors struggle to assess the status of collaborative inquiries efficiently and provide feedback to students effectively due to increasing class sizes and the vast amounts of discourse data generated. This struggle further diminishes the quality of student learning. In this context, this project introduces an innovative solution in the form of an easy-to-use and user-friendly analytical module powered by artificial intelligence (AI). Guided by the community of inquiry (CoI) theoretical model, this analytical module automatically processes discourse data, models students’ inquiry patterns, and generates visualizations and explanations to inform instructors’ decision-making. This analytical module holds great potential in assisting and enhancing instructors’ formative assessment and feedback practices. During the project period, the analytical module will directly impact 200 to 300 undergraduate and graduate students in several inquiry-based courses (e.g., HPI 2001 Honours Project, CPI 2001 Capstone Project, and PRJ6003 Practitioner-based Research Project). Quasi-experiments will be conducted to explore the effects of AI-assisted formative assessment and feedback on students’ inquiry patterns and perceived feedback effectiveness. In addition, 30 to 50 staff members will benefit from attending workshops and seminars on this project’s design and findings.In the long term, this project aims to extend the reach of the proposed analytical module to all inquiry-based courses in EdUHK and beyond, optimizing the way collaborative inquiries are assessed and feedback is provided. The outcomes and findings of this project will not only provide a sustainable and generalizable path for incorporating AI into teaching and learning processes but also significantly enhance students' achievement of intended learning outcomes, especially problem-solving and critical thinking skills.
Project Start Year: 2024, Principal Investigator(s): BA, Shen
SDGs Information: 4 - Quality Education, 9 - Industry, Innovation and Infrastructure, 10 - Reduced Inequality
 
Exploring the usage and effectiveness of GAI in university students’ inquiry-based learning
This project addresses the intersection of artificial intelligence (AI) and education, with a particular focus on generative AI (GAI) and its role in facilitating inquiry-based learning among university students. With the rapid and irreversible development of various GAI products (e.g., ChatGPT), the conventional way of teaching and learning in higher education is facing challenges, including how students obtain information, generate ideas, and develop skills. On the one hand, GAI can contribute greatly to students’ learning by being available 24/7, answering any type of questions, and offering immediate feedback. On the other hand, inappropriate usage of or overly reliance on GAI can also hinder learning and lead to serious issues such as plagiarism and dishonesty. With such distinct advantages and disadvantages of GAI, it is important to identify how students use GAI during the learning process and determine patterns and strategies that are beneficial to learning while minimizing the negative effects. This project aims to employ a mix of quantitative, qualitative, and computational methods to explore how university students use GAI in inquiry-based learning activities and to assess the effectiveness of GAI in facilitating students’ various learning outcomes. The findings of this project will 1) reveal students’ typical types of GAI usages; 2) demonstrate good and bad practices of GAI and their impact on learning outcomes; and 3) inform the designs of guidelines and strategies guiding GAI-assisted inquiry-based learning.
Project Start Year: 2024, Principal Investigator(s): BA, Shen
SDGs Information: 4 - Quality Education
 
Research Outputs
Journal Publications
Ba, S., & Hu, X. (2025). Effects of background music tempo and mode on reading comprehension: the mediating role of emotions. Instructional Science, 00, 00. https://doi.org/10.1007/s11251-025-09728-5
SDGs infomation: 4 - Quality Education, 5 - Gender Equality, 10 - Reduced Inequality
Ba, S., Zhan, Y., Huang, L., & Liu, G. (2025). Investigating the impact of ChatGPT‐assisted feedback on the dynamics and outcomes of online inquiry‐based discussion. British Journal of Educational Technology, 0, 0. https://doi.org/10.1111/bjet.13605
SDGs infomation: 4 - Quality Education, 17 - Partnerships for the Goals
Lu, G. & Ba, S. (2025). Exploring the impact of GAI-assisted feedback on pre-service teachers’ situational engagement and performance in inquiry-based online discussion. Educational Psychology, 1-26. https://doi.org/10.1080/01443410.2025.2489784
SDGs infomation: 4 - Quality Education
Huang, L. , Zhan, Y., & Ba, S. (2025). Modeling student teachers’ self-regulated learning of complex professional knowledge: A sequential and clustering analysis with think-aloud protocols. Computers and Education, 233, Article 105310. https://doi.org/10.1016/j.compedu.2025.105310
SDGs infomation: 4 - Quality Education
Ba, S., Hu, X., Stein, D., & Liu, Q. (2024). Anatomizing online collaborative inquiry using directional epistemic network analysis and trajectory tracking. British Journal of Educational Technology, 00, 1-19. https://doi.org/10.1111/bjet.13441
Ba, S., & Hu, X. (2023). Measuring emotions in education using wearable devices: A systematic review. Computers and Education, 200, Article 104797. https://doi.org/10.1016/j.compedu.2023.104797
SDGs infomation: 4 - Quality Education, 9 - Industry, Innovation and Infrastructure, 11 - Sustainable Cities and Communities
Ba, S., Hu, X., & Law, N. (2023). Daily activities and social interactions predict students’ positive feelings. Asia Pacific Journal of Education. https://doi.org/10.1080/02188791.2023.2219414
SDGs infomation: 3 - Good Health and Well-Being, 4 - Quality Education
Ba, S., Hu, X., Stein, D., & Liu, Q. (2023). Assessing cognitive presence in online inquiry-based discussion through text classification and epistemic network analysis. British Journal of Educational Technology, 54(1), 247-266. https://doi.org/10.1111/bjet.13285
SDGs infomation: 4 - Quality Education
Yu, S., Liu, Q., Johnson-Glenberg, M.C., Han, M., Ma, J., Ba, S., & Wu, L. (2023). Promoting musical instrument learning in virtual reality environment: Effects of embodiment and visual cues. Computers and Education, 198, Article 104764. https://doi.org/10.1016/j.compedu.2023.104764
SDGs infomation: 4 - Quality Education
李小娟、付斯理、張翼恒、巴深和鄧偉 (2023). 網絡學習空間中虛擬教師的社會形象研究. 現代教育技術, 5, 99-108. https://doi.org/CNKI:SUN:XJJS.0.2023-05-012
SDGs infomation: 4 - Quality Education
Yu, S., Liu, Q., Ma, J., Le, H., & Ba, S. (2022). Applying Augmented reality to enhance physics laboratory experience: Does learning anxiety matter?. Interactive Learning Environments, 31(10), 6952-6967. https://doi.org/10.1080/10494820.2022.2057547
SDGs infomation: 4 - Quality Education
Ba, S., Stein, D., Liu, Q., Long, T., Xie, K., & Wu, L. (2021). Examining the effects of a pedagogical agent with dual-channel emotional cues on learner emotions, cognitive load, and knowledge transfer performance. Journal of Educational Computing Research, 59(6), 1114-1134. https://doi.org/10.1177/0735633121992421
SDGs infomation: 4 - Quality Education, 5 - Gender Equality
巴深、劉清堂、吳林靜和余欽春 (2021). 教育智能體情緒線索對大學生學習情緒與動機的影響研究. 遠程教育雜誌, 6, 48-57. https://doi.org/10.15881/j.cnki.cn33-1304/g4
SDGs infomation: 4 - Quality Education
Liu, Q., Huang, J., Wu, L., Zhu, K., & Ba, S. (2020). CBET: Design and evaluation of a domain-specific chatbot for mobile learning. Universal Access in the Information Society, 19, 655-673. https://doi.org/10.1007/s10209-019-00666-x
SDGs infomation: 4 - Quality Education
劉清堂、巴深、余舒凡、張翼恒和張妮 (2020). 視頻課程中教育智能體的社會線索設計研究. 電化教育研究, 9, 55-66. https://doi.org/10.13811/j.cnki.eer.2020.09.008
SDGs infomation: 4 - Quality Education
張妮、劉清堂、徐彪、羅磊、陳越和巴深 (2020). 支持教師區域研修的 PAST 模型構建及應用研究. 中國電化教育, 4, 93-101. https://doi.org/CNKI:SUN:ZDJY.0.2020-04-019
SDGs infomation: 4 - Quality Education
劉清堂、巴深、羅磊、張翼恒和吳林靜 (2019). 教育智能體對認知學習的作用機制研究述評. 遠程教育雜誌, 5, 35-44. https://doi.org/10.15881/j.cnki.cn33-1304/g4.2019.05.005
SDGs infomation: 4 - Quality Education
劉清堂、黃景修、蔣志輝、張妮和巴深 (2019). 面向線上討論的時間序列建模實驗. 現代教育技術, 5, 39-45. https://doi.org/CNKI:SUN:XJJS.0.2019-05-007
SDGs infomation: 4 - Quality Education
吳林靜、勞傳媛、劉清堂、黃景修和巴深 (2019). 基於依存句法的初等數學分層抽樣應用題題意理解. 計算機應用與軟件, 5, 126-132. https://doi.org/CNKI:SUN:JYRJ.0.2019-05-024
SDGs infomation: 4 - Quality Education

Conference Papers
Yang, Q., Lu, G., Ba, S., Cui, L., & Wang, L. (2025, July). Exploring the effect of academic motivation on learning outcomes: The mediating role of GAI technology acceptance. 11th International Symposium on Educational Technology, Bangkok, Thailand.
SDGs infomation: 4 - Quality Education
Wang, Y., Li, K. Y., & Ba, S. (2025, April). Evaluating the impact of audiovisual feedback tools on pre-service music teachers' self-assessment. American Educational Research Association Annual Meeting, Denver, CO, USA.
SDGs infomation: 4 - Quality Education
Ba, S., Chen, Y., Tan, Y., Lu, G., & Shaffer, D. W. (2025, March). Aligning analytics with theory: A customized epistemic network analysis rotation for the practical inquiry model. 15th International Conference on Learning Analytics & Knowledge, Dublin, Ireland.
SDGs infomation: 4 - Quality Education
Ba, S., & Lu, G. (2024, November). Inquiry-based discussion with ChatGPT: Preliminary insights from epistemic network analysis. Sixth International Conference on Quantitative Ethnography, Philadelphia, PA, USA.
SDGs infomation: 4 - Quality Education
Ba, S., & Hu, X. (2023). Exploring eye movements in virtual heritage environment with epistemic network analysis. Fifth International Conference on Quantitative Ethnography, Melbourne, VIC, Australia.
SDGs infomation: 4 - Quality Education
Liu, R., Wang, Z., Ba, S., & Hu, X. (2023). Preliminary exploration of the effectiveness of music listening and music recommender for studying in naturalistic settings. Proceedings of 2023 IEEE International Conference on Advanced Learning Technologies, ICALT 2023, Orem, UT, USA. https://doi.org/10.1109/ICALT58122.2023.00055
SDGs infomation: 4 - Quality Education
Wang, C., Ba, S., Hu, X., & Shao, Y. (2023). Exploring factors limiting participation in an online training program for college teachers from developing countries. Proceedings of 2023 IEEE International Conference on Advanced Learning Technologies, ICALT 2023 https://doi.org/10.1109/ICALT58122.2023.00054
SDGs infomation: 4 - Quality Education, 5 - Gender Equality
Ba, S., Hu, X., Kong, R., & Law, N. (2022). Supporting adolescents’ digital well-being in the post-pandemic era: Preliminary results from a multimodal learning analytics approach. Proceedings of 2022 International Conference on Advanced Learning Technologies (ICALT 2022) https://doi.org/10.1109/ICALT55010.2022.00059
SDGs infomation: 3 - Good Health and Well-Being, 4 - Quality Education
Liu, Q., Yu, Q., & Ba, S. (2021). The design and development of a classroom evaluation system for K-12 formative assessment in China. Proceedings of 2021 International Symposium on Educational Technology, ISET 2021 https://doi.org/10.1109/ISET52350.2021.00047
SDGs infomation: 4 - Quality Education
Liu, Q., Xu, S., Yu, S., Yang, Y., Wu, L., & Ba, S. (2019). Design and implementation of an AR-based inquiry courseware: Magnetic field. Proceedings of 2019 International Symposium on Educational Technology (ISET 2019) https://doi.org/10.1109/ISET.2019.00036
SDGs infomation: 4 - Quality Education
Liu, Q., Yang, H., Ba, S., Wang, Y., & Zhao, W. (2019). Blended learning using mobile APP in secondary vocational instruction: Design and implementation. Proceedings of the 10th International Conference on E-Education, E-Business, E-Management and E-Learning https://doi.org/10.1145/3306500.3306544
SDGs infomation: 4 - Quality Education
Liu, Q., Ba, S., Wu, L., Huang, J., & Li, H. (2018). Virtual dulcimer auxiliary teaching system based on musical instrument digital interface. Proceedings of 2018 International Symposium on Educational Technology (ISET 2018) https://doi.org/10.1109/ISET.2018.00027
SDGs infomation: 4 - Quality Education
Liu, Q., Ba, S., Huang, J., Wu, L., & Lao, C. (2017). A study on grouping strategy of collaborative learning based on clustering algorithm. Blended learning: New challenges and innovative practices: 10th International Conference, ICBL 2017, Hong Kong, China, June 27-29, 2017, proceedings https://doi.org/10.1007/978-3-319-59360-9_25
SDGs infomation: 4 - Quality Education