Dr POON, Kin Man   潘建文
Associate Head / Associate Professor
Department of Mathematics and Information Technology
Phone No: (852) 2948 8974
Email: kmpoon@eduhk.hk
Contact
ORCiD
0000-0002-8394-1492
Phone
(852) 2948 8974
Email
kmpoon@eduhk.hk
Scopus ID
53464057700, 36470725300
Research Interest

Clustering, latent variable models, probabilistic graphical models, natural language processing, machine learning, AI in education

External Appointment

Senior PC Member:

  • International Joint Conference on Artificial Intelligence (IJCAI): 2016, 2017, 2019-20

PC Member:

  • AAAI Conference on Artificial Intelligence (AAAI): 2016-20
  • Conference on Neural Information Processing Systems (NeurIPS): 2018-19
  • Conference on Uncertainty in Artificial Intelligence (UAI): 2014-20
  • International Conference on Artificial Intelligence and Statistics: 2020
  • International Conference on Machine Learning (ICML): 2015, 2019-20
  • International Joint Conference on Artificial Intelligence (IJCAI): 2015, 2018
  • Australasian Joint Conference on Artificial Intelligence: 2019
  • International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC): 2019
  • International Conference on Computer and Communication Systems (ICCCS): 2018-20
  • International Conference on Computers in Education (ICCE): 2014
  • International Conference on Technology in Education (ICTE): 2014

Journal Reviewer:

  • Computers & Education: 2019
  • Design Science: 2019
  • Experimental Gerontology: 2017
  • IEEE Access: 2019
  • IEEE Transactions on Biomedical Engineering: 2019
  • International Journal of Information Technology and Decision Making: 2015
  • Stat: 2019

Professional Profile

Leonard Kin-Man Poon is a faculty member in the Department of Mathematics and Information Technology at The Education University of Hong Kong. He received his PhD and MPhil degrees in computer science and his BEng degree in electronic engineering from The Hong Kong University of Science and Technology. He has previously worked as a part-time lecturer at HKU SPACE Community College, and as a software developer at Reuters and EDS.

Research Interest

Clustering, latent variable models, probabilistic graphical models, natural language processing, machine learning, AI in education

External Appointment

Senior PC Member:

  • International Joint Conference on Artificial Intelligence (IJCAI): 2016, 2017, 2019-20

PC Member:

  • AAAI Conference on Artificial Intelligence (AAAI): 2016-20
  • Conference on Neural Information Processing Systems (NeurIPS): 2018-19
  • Conference on Uncertainty in Artificial Intelligence (UAI): 2014-20
  • International Conference on Artificial Intelligence and Statistics: 2020
  • International Conference on Machine Learning (ICML): 2015, 2019-20
  • International Joint Conference on Artificial Intelligence (IJCAI): 2015, 2018
  • Australasian Joint Conference on Artificial Intelligence: 2019
  • International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC): 2019
  • International Conference on Computer and Communication Systems (ICCCS): 2018-20
  • International Conference on Computers in Education (ICCE): 2014
  • International Conference on Technology in Education (ICTE): 2014

Journal Reviewer:

  • Computers & Education: 2019
  • Design Science: 2019
  • Experimental Gerontology: 2017
  • IEEE Access: 2019
  • IEEE Transactions on Biomedical Engineering: 2019
  • International Journal of Information Technology and Decision Making: 2015
  • Stat: 2019

Selected Output

Scholarly Books, Monographs and Chapters
Poon, L. K. M. (2019). Extracting access patterns with hierarchical latent tree analysis: An empirical study on an undergraduate programming course. In H. Seki, C. H. Nguyen, V.-N. Huynh, & M. Inuiguchi (Eds.), Integrated Uncertainty in Knowledge Modelling and Decision Making. IUKM 2019. LNCS, vol 11471 (pp. 380-392). Cham: Springer.
Poon, L. K. M. (2018). GPU-accelerated clique tree propagation for pouch latent tree models. In F. Zhang, J. Zhai, M. Snir, H. Jin, H. Kasahara, & M. Valero (Eds.), Network and Parallel Computing. NPC 2018. LNCS, vol 11276 (pp. 90-102). Cham: Springer.
Poon, L. K. M., Kong, S. C., Wong, M. Y. W., & Yau, T. S. H. (2017). Mining sequential patterns of students’ access on learning management system. In Y. Tan, H. Takagi, & Y. Shi (Eds.), Data Mining and Big Data. DMBD 2017. LNCS, vol 10387 (pp. 191-198). Cham: Springer.
Poon, L. K. M., Leung, C. F., & Zhang, N. L. (2017). Mining textual reviews with hierarchical latent tree analysis. In Y. Tan, H. Takagi, & Y. Shi (Eds.), Data Mining and Big Data. DMBD 2017. LNCS, vol 10387 (pp. 401-408). Cham: Springer.
Poon, L. K. M., Leung, C. F., Chen, P., & Zhang, N. L. (2017). Topic browsing system for research papers based on hierarchical latent tree analysis. In L. Chen, C. S. Jensen, C. Shahabi, X. Yang, & X. Lian (Eds.), Web and Big Data. APWeb-WAIM 2017. LNCS, vol 10367 (pp. 341-344). Cham: Springer.
Poon, L. K. M. (2017). Clustering with Multidimensional Mixture Models: Analysis on World Development Indicators. In F. Cong, A. Leung, & Q. Wei (Eds.), Advances in Neural Networks - ISNN 2017. ISNN 2017. LNCS, vol 10261 (pp. 153-160). Cham: Springer.
Poon, L. K. M., Kong, S. C., Yau, T. S. H., Wong, M., & Ling, M. H. (2017). Learning analytics for monitoring students’ participation online: Visualizing navigational patterns on learning management system. In S. K. Cheung, L.-F. Kwok, W. W. Ma, L.-K. Lee, & H. Yang (Eds.), Blended Learning. New Challenges and Innovative Practices. ICBL 2017. LNCS, vol 10309 (pp. 166-176). Cham: Springer.
Poon, L. K. M., Li, Z., & Cheng, G. (2017). Topic classification on short reflective writings for monitoring students’ progress. In S. K. Cheung, L.-F. Kwok, W. W. Ma, L.-K. Lee, & H. Yang (Eds.), Blended Learning. New Challenges and Innovative Practices. ICBL 2017. LNCS, vol 10309 (pp. 236-246). Cham: Springer.

Journal Publications
Poon, L. K. M., Ng, W. S., & Cheng, G. (2020). Automatic Topic Detection on Chinese Essays: A Technology Enhanced Approach for Facilitating Formative Use of Summative Assessment. International Journal of Mobile Learning and Organization, xx, xx-xx.
Huang, M., Xie, H., Rao, Y., Liu, Y., Poon, L. K. M., & Wang, F. L. (2020). Lexicon-Based Sentiment Convolutional Neural Networks for Online Review Analysis. IEEE Transactions on Affective Computing, xx, xx-xx.
Chen, X., Xie, H., Cheng, G., Poon, L. K. M., Leng, M., & Wang, F. L. (2020). Trends and Features of the Applications of Natural Language Processing Techniques for Clinical Trials Text Analysis. Applied Sciences, 10(6), 2157.
Poon, L. K. M., Liu, A. H., & Zhang, N. L. (2018). UC-LTM: Unidimensional clustering using latent tree models for discrete data. International Journal of Approximate Reasoning, 92, 392-409.
Chen, P., Zhang, N. L., Liu, T., Poon, L. K. M., Chen, Z., & Khawar, F. (2017). Latent tree models for hierarchical topic detection. Artificial Intelligence, 250, 105-124.
Zhang, N. L., Fu, C., Liu, T. F., Chen, B.-X., Poon, K. M., Chen, P. X., & Zhang, Y.-L. (2017). A data-driven method for syndrome type identification and classification in traditional Chinese medicine. Journal of Integrative Medicine, 15 (2), 110-123.
Liu, T.-F., Zhang, N. L., Chen, P., Liu, A. H., Poon, L. K. M., & Wang, Y. (2015). Greedy Learning of Latent Tree Models for Multidimensional Clustering. Machine Learning, 98 (1-2), 301-330.
Liu, A. H., Poon, L. K. M., Zhang, N. L., & Liu, T. (2014). Latent Tree Models for Rounding in Spectral Clustering. Neurocomputing, 144, 448-462.
Wang, Y., Zhang, N. L., Chen, T., & Poon, L. K. M. (2013). LTC: A latent tree approach to classification. International Journal of Approximate Reasoning, 54(4), 560-572.
Poon, L. K. M., Zhang, N. L., Liu, T., & Liu, A. H. (2013). Model-based clustering of high-dimensional data: Variable selection versus facet determination. International Journal of Approximate Reasoning, 54(1), 196-215.
Chen, T., Zhang, N. L., Liu, T., Poon, K. M., & Wang, Y. (2012). Model-based multidimensional clustering of categorical data. Artificial Intelligence, 176(1), 2246-2269.

Conference Papers
Khawar, F., Poon, L. K. M., & Zhang, N. L. (2020, April). Learning the Structure of Auto-Encoding Recommenders. In Proceedings of The Web Conference (WWW '20), Taiwan.
Cheng, G., Poon, L. K. M., Lau, W. W. F., & Zhou, R. C. (2019, July). Applying Eye Tracking to Identify Students’ Use of Learning Strategies in Understanding Program Code. Proceedings of the 3rd International Conference on Education and Multimedia Technology (ICEMT 2019), Nagoya, Japan.
Li, X., Chen, Z., Poon, L. K. M., & Zhang, N. L. (2019, May). Learning latent superstructures in variational autoencoders for deep multidimensional clustering. The Seventh International Conference on Learning Representations, New Orleans, US.
Cheng, G., Poon, L. K. M., Lau, W. W. F., & Zhou, R. C. (2019, April). Exploring the Relationship between Self-Regulated Learning Strategies and Computer Programming Achievement in Higher Education. Proceedings of the 5th International Conference on Education (ICEDU 2019), Kuala Lumpur, Malaysia.
Poon, L. K. M., Zhang, N. L., Xie, H., & Cheng, G. (2018, April). Handling Collocations in Hierarchical Latent Tree Analysis for Topic Modeling. Paper presented in the 3rd International Conference on Computer and Communication Systems, Nagoya, Japan.
Hu, H., Poon, K. M., & Hu, C. (2017, August). Opinion Target Extraction(OTE) model training and applying OTE to facilitate web app development. Paper presented in the IV International AMMCS Interdisciplinary Conference, Waterloo, Canada.
Zhang, N. L., & Poon, L. K. M. (2017, February). Latent Tree Analysis. The Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17), San Francisco, US.
Chen, P., Zhang, N. L., Poon, L. K. M., & Chen, Z. (2016, February). Progressive EM for Latent Tree Models and Hierarchical Topic Detection. The Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, US.
Liu, A. H., Poon, L. K. M., & Zhang, N. L. (2015, January). Unidimensional Clustering of Discrete Data using Latent Tree Models. The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI-15), Austin, US.
Liu, T., Zhang, N. L., Poon, K. M., Liu, H., & Wang, Y. (2012, September). A novel LTM-based method for multi-partition clustering. Sixth European Workshop on Probabilistic Graphical Models, Granada, Spain.
Poon, L. K. M., Liu, A. H., Liu, T., & Zhang, N. L. (2012, August). A model-based approach to rounding in spectral clustering. In Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence (UAI-12), Catalina Island, United States.
T. Liu, N. L. Zhang, L. K. M. Poon, Y. Wang, and H. Liu (2011, September). Fast multidimensional clustering of categorical data. In Proceedings of the 2nd MultiClust Workshop: Discovering, Summarizing and Using Multiple Clusterings, Athens, Greece.
Wang, Y., Zhang, N. L., Chen, T., & Poon, L. K. M. (2011, June). Latent tree classifier. ECSQARU 2011: Symbolic and Quantitative Approaches to Reasoning with Uncertainty, Belfast, UK.
Poon, L. K. M., Zhang, N. L., Chen, T., & Wang, Y. (2010, November). Using Bayesian networks for model-based multiple clusterings: An example of exploratory analysis on NBA Data. In The 1st International Workshop on Advanced Methodologies for Bayesian Networks, Tokyo, Japan.
Poon, L. K. M., Zhang, N. L., Chen, T., & Wang, Y. (2010, June). Variable selection in model-based clustering: To do or to facilitate. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel.

Project

Establishing a Research Cluster for Promoting Artificial Intelligence in Technology-Enhanced Language Learning (AI-TELL) Research
This project aims to propose and establish a research cluster to promote artificial intelligence in technology-enhanced language learning (hereafter, AI-TELL) research in Hong Kong. The ultimate goal of the proposed AI-TELL research cluster is to identify and bridge the gap between AI techniques and TELL towards developing pedagogical innovations to enhance language learning.
Project Start Year: 2020, Principal Investigator(s): CHENG, Kwok Shing 鄭國城 (POON, Kin Man 潘建文 as Co-Investigator)
 
Facilitating Artificial Intelligence and Big Data Analytics Research in Education
This project aims to develop AI in education and big data analytics in education as the departmental strategic areas. It is also planned to facilitate the development of the two areas through various related research activities, which include organizing research seminars, undertaking collaborative research, and inviting world-leading scholars for discussion and consultation
Project Start Year: 2020, Principal Investigator(s): CHENG, Kwok Shing 鄭國城 (POON, Kin Man 潘建文 as Co-Investigator)
 
Latent Variable Models for Multifaceted Subspace Clustering
In this project, we aim to develop a solution for the problem of finding multiple clusterings of data points residing in different subspaces on a data set. We refer to such a problem as multifaceted subspace clustering. The solution will be based on probabilistic models due to their sound statistical basis. The proposed models will contain multiple discrete latent variables to represent multiple clusterings along different facets. To represent the local subspaces in each clustering, we will cons . . .
Project Start Year: 2020, Principal Investigator(s): POON, Kin Man 潘建文
 
Promoting AI Literacy and Effective Use of AI in Education
The objectives of this project are twofold: firstly to prepare students with AI literacy and secondly to explore and develop AI tools for teaching and learning in a range of academic disciplines. The project will offer a good opportunity not only to develop the AI literacy of students, but also to promote effective use of AI in education as well as to prepare students to adopt AI-powered technology in their future teaching careers.
Project Start Year: 2020, Principal Investigator(s): LI, Wai Keung 李偉強 (POON, Kin Man 潘建文 as Co-Investigator)
 
Emotion Detection for Discussion Logs in Collaborative Learning with Hybrid Neural Networks
To address the above problem, this project aims to develop a deep neural network, one of the recent techniques in artificial intelligence, to detect emotional signals form discussion logs of the collaborative learning process automatically.
Project Start Year: 2019, Principal Investigator(s): POON, Kin Man 潘建文
 
Explorative Study on Text Mining Techniques for Facilitating Formative Use of Summative Assessment
Essay writing is an important form of assessment. It is typically used as summative assessment and may not have some of the major benefits of formative assessment. Although there are considerations of formative use of summative assessment, such use remains limited in practice. It is because of the difficulty in presenting the results and the large amount of effort required. In this project, we aim to explore the use of text mining techniques to facilitate formative use of summative assessment . . .
Project Start Year: 2019, Principal Investigator(s): POON, Kin Man 潘建文
 
Extracting Co-Occurring Access Patterns of Students for Building Learning Analytics
Students perform many online learning activities nowadays. Many online platforms allow us to log the students’ access to those activities easily. This log data may potentially provide abundant insight to the learning status of the students. In this project, we propose a novel method to extract access patterns of the students by capturing the co-occurrences of accesses. The proposed method is based on a recent topic detection method that has been shown to have superior performance over several st . . .
Project Start Year: 2019, Principal Investigator(s): POON, Kin Man 潘建文
 
Humanoid and Virtual Learning and Teaching Environment for STEM Education
This project aims to establish an infrastructure for innovative learning and teaching with humanoid and virtual reality environment in STEM Education. A cloud server will be established to support the humanoid and virtual reality interaction. Situated learning, anchored instruction, growth mindset and collaborative learning are the core theoretical underpinnings to this research project. We will program a situated mathematical learning scenario anchored on different learning aspects to be deploy . . .
Project Start Year: 2019, Principal Investigator(s): SO, Wing Wah Simon 蘇永華 (POON, Kin Man 潘建文 as Co-Investigator)
 
Infuse STEM/STEAM elements into Mathematics and Information Technology Courses
This project aims to infuse STEM/STEAM elements into our subject-based courses in Mathematics and Information Technology courses. For each learning area of the subject-based courses, a relevant exemplar will be established to integrate STEM/STEAM elements into the teaching and learning of the subject. Instructional materials for each exemplar will be designed and implemented by a team of developers in consultation with the project’s supervisors. The materials will be freely available online to t . . .
Project Start Year: 2019, Principal Investigator(s): SO, Wing Wah Simon 蘇永華 (POON, Kin Man 潘建文 as Co-Investigator)
 
Tracking Students’ Use of Self-Regulated Learning Strategies for Computer Programming in Teacher Education
This project aims to draw on the concept of self-regulated learning (SRL) to engage student teachers in goal setting, progress monitoring and strategic management through electronic portfolio (ePortfolio). Students’ use of SRL strategies to attain specific learning goals will be identified from a multitude of data sources, including their written reflective entries on the e-Portfolio platform, their eye-tracking and think-aloud data recorded in a computer lab, as well as their verbal feedback co . . .
Project Start Year: 2019, Principal Investigator(s): CHENG, Kwok Shing 鄭國城 (POON, Kin Man 潘建文 as Co-Investigator)
 
A Pilot Study on a Smartphone-based Intervention in Overweight Middle-aged Adults
..
Project Start Year: 2018, Principal Investigator(s): CHEUNG, Pui Yee Peggy 張佩儀 (POON, Kin Man 潘建文 as Co-Investigator)
 
A Study of Online Evidence-based Assessment System to Promote Collaborative and Cooperative Learning in Group Activities
Many courses involve group projects and/or activities to let students to collaborate and work together to solve problems. However, it is not easy to ensure all students are actively contributed and collaborate with each other to complete the project. As teachers usually collect the final outcome and mark it as a whole, it is difficult to assess the group project fairly within a group if the workload is unevenly distributed. In this project, we proposed to use “An Online Evidence-based Assessment . . .
Project Start Year: 2018, Principal Investigator(s): LAM, Wai Man Winnie 林惠民 (POON, Kin Man 潘建文 as Co-Investigator)
 
Detection of Stress and Depressive Symptomatology among Dementia Family Caregivers: Using Sensors Embedded in Smartphone
This project aims to establish the validity and reliability of the social-behavioral measures that are used to detect overburden family caregivers of dementia patients using data collected by sensors embedded in smartphones.
Project Start Year: 2018, Principal Investigator(s): POON, Kin Man 潘建文
 
Explorative Study on Text Summarization and Sentiment Analysis with Hierarchical Latent Tree Analysis
This project aims to explore how hierarchical latent tree analysis can be used for text summarization and sentiment analysis.
Project Start Year: 2018, Principal Investigator(s): POON, Kin Man 潘建文
 
Developing and Evaluating a Learning Analytics Platform to Support University Teachers for Pedagogical Decision-making in Fostering Reflective Engagement of Students
The project aims to develop a learning analytics platform conducive to data-oriented decision-making; to evaluate the impact of a learning analytics platform on facilitating reflective engagement of students in the learning process; and to evaluate the impact of a learning analytics platform on teachers’ pedagogical decision making. The expected outcomes include a deliverable learning analytics platform, which can help teachers gain a better understanding of students’ learning process, and ident . . .
Project Start Year: 2014, Principal Investigator(s): KONG, Siu Cheung 江紹祥, SONG, Yanjie 宋燕捷, POON, Kin Man 潘建文
 
Bring Your Own Device (BYOD) for Reflective Engagement of Learners in Digital Classroom
The project aims to enhance the competency of HKIEd academic/teaching staff in promoting learners’ reflective engagement in line with HKIEd e-learning strategies. The project has the objectives to enhance the reflective engagement of learners in course learning in HKIEd; to enhance the reflective engagement of lecturers in course teaching in HKIEd; to enhance the sustainability of e-learning implementation in course learning and teaching in HKIEd; and to enhance the scalability of e-learning imp . . .
Project Start Year: 2013, Principal Investigator(s): KONG, Siu Cheung 江紹祥, CHUNG, Wai Yee Joanne 鍾慧儀, SONG, Yanjie 宋燕捷 (POON, Kin Man 潘建文 as Co-Investigator)
 
Extending Gaussian mixture models and factor models for data analysis
We plan to extend Gaussian mixture models and factor models using pouch latent tree models. The new models can be used for data analysis.
Project Start Year: 2013, Principal Investigator(s): POON, Kin Man 潘建文
 
Using latent tree models for collaborative filtering
With lot of information online available, we are often faced with too many choices. To reduce the number of choices to a manageable number, recommender systems have been used. A popular approach in recommender systems is collaborative filtering. It builds on the idea that users who have shared interest in the past will have similar tastes in the future. This project aims to develop a new model-based method for collaborative filtering.
Project Start Year: 2013, Principal Investigator(s): POON, Kin Man 潘建文
 
Prizes and awards

Special Inventor Award
In iCAN 2019, EdUHK showcased four edtech innovations and the GMoodle system for assessment automation has been awarded with two prizes: silver medal and special award. The GMoodle system is developed for assessment of collaborative learning. The whole process of collaboration is recorded by the system to provide an objective measure and fair evaluation to reflect the actual contribution of each student in a group project.
Date of receipt: 24/8/2019, Conferred by: The International Invention Innovation Competition in Canada (iCAN) 2019
 
Silver Medal
In iCAN 2019, EdUHK showcased four edtech innovations and the GMoodle system for assessment automation has been awarded with two prizes: silver medal and special award. The GMoodle system is developed for assessment of collaborative learning. The whole process of collaboration is recorded by the system to provide an objective measure and fair evaluation to reflect the actual contribution of each student in a group project.
Date of receipt: 24/8/2019, Conferred by: The International Invention Innovation Competition in Canada (iCAN) 2019