web stats
Selected Development Project
Project Title

Automatic Classification Techniques In Virtual Environments – The ACTIVE Project: Generating Immediate Feedback to Support Reflective Learning within ePortfolio Contexts
虛擬環境中的自動分類技術 - ACTIVE專案:產生即時回饋以支援學習歷程系統中的反思性學習

Principal Investigator Dr Cheng, Kwok Shing
Area of Research Project
Teaching and Learning
Project Period
From 01/2014 To 12/2015
  • To develop an automatic classification tool for identifying different levels of student reflection and generating adaptive feedback based on the identification results;
  • To evaluate the agreement of identification results between the tool and human annotators;
  • To examine the impact of the tool on the level of student reflection; and
  • To collect and analyse students’ and teachers’ views on the role of the tool in reflective learning.
Methods Used
  • To build an automatic classification tool based on a corpus of annotated reflective entries and latent semantic analysis;
  • To measure consistency in the results on a testing set of reflective entries between the tool and human annotators;
  • To examine statistical differences in the level of reflection between students who use the tool and those who do not; and
  • To conduct semi-structured interviews with students and teachers in order to elicit their views about the tool.
Summary of Findings
  • It is expected that students would generally agree that the results generated by the tool can help identify their strengths and limitations in reflective learning
  • To provide students with immediate and adaptive feedback on their reflective entries within the ePortfolio context;
  • To help teachers monitor students’ progress in reflective learning easily and systematically;
  • To gain a better understanding of the development and effectiveness of the automatic classification tool in fostering students’ reflective learning; and
  • To act as a reference for other types of virtual learning environments such as online discussion forums and wikis where their automatic assessment methods are based on the quantity rather than the quality of student postings.
  • Cheng, G., & Chau, J. (2013). An Approach to Identify Levels of Reflection Using Latent Semantic Analysis. Proceedings of the 3rd International Conference on IT Convergence and Security (ICITCS 2013), Dec 16 -18, 2013, Macau, China.
Biography of Principal Investigator
Dr. Cheng is currently an academic staff in the Department of Mathematics and Information Technology at HKIEd. Prior to joining HKIEd in June 2012, he has held various positions, including Lecturer, Educational Designer and Systems Consultant (Outcome-Based Teaching & Learning) in a number of tertiary institutions at Hong Kong. 
Funding Source

General Research Fund