web stats
Selected Development Project
Project Title

Towards Automatic Tracking of Student Responses to Teacher Feedback in Draft Revision

Principal Investigator Dr CHENG Kwok Shing Gary
Area of Research Project
Teaching and Learning
Project Period
From 01/2017 To 12/2018
  1. To develop an automatic classification system for identifying types of teacher feedback and student revisions as well as detecting connections between them;
  2. To evaluate the agreement of results between machine and human classification;
  3. To examine the impact of the system on the quality of students’ final drafts; and
  4. To explore views of students and teachers on the role of the system in the teaching and learning process of essay writing.
Methods Used

In this project, a data set of teacher feedback and student revisions was compiled and annotated to develop a computerized system that classifies teacher feedback and student revisions into categories and tracks the mappings between them. The system can provide an analysis of: (1) classifications of teacher feedback and students revisions, and (2) how well students make revisions in response to the feedback they received. Experimental and control groups were involved to evaluate how effective the automated analysis would be in helping students improve their writing performance. Students in the experimental group were given access to the automated tracking system, while their counterparts in the control group were not. Additionally, an online questionnaire and semi-structured interviews were used to explore students’ and teachers’ views on the role of the automated tracking system in the teaching and learning process of essay writing.

Summary of Findings

The findings of this project indicate that:

  1. The automated tracking system could perform very well in terms of the accuracy of classifying teacher feedback and student revisions as well as identifying the connections between them.
  2. Teachers tended to overwhelmingly use the most controlling feedback types (i.e. criticism and imperative), but the use pattern of feedback types varied across teachers.
  3. Students’ essay grades were correlated more with certain types of teacher feedback (e.g. praise, criticism and imperative) and less with others (e.g. advice and question).
  4. The automated tracking system could help students reflect on gaps between the feedback received and their revisions, thereby encouraging more effective revisions and a higher quality of writing.

The project has the following impacts:

  1. It is significant in automatically generating immediate, adaptive and individualized feedback to facilitate students’ reflection on their responses to teacher feedback in draft revision.
  2. It is important in providing teachers with indicators to monitor students’ progress and identify those having problems in revising their drafts.
  3. It can contribute to proposing a practical and scalable approach that could help analyze a large volume of teacher feedback and student revisions, and to gaining a fuller understanding of the impact of different types of teacher feedback on student revisions.
Selected Output

Cheng, G., Chen, J., Foung, D., Lam, V., & Tom, M. (2018). Towards automatic classification of teacher feedback on student writing. International Journal of Information and Education Technology, 8(5), 342-346.

Cheng, G., Chwo, S.-M. G., Chen, J., Lam, V., Law, E., & Lai, R. (2018, July). Exploring the relationship between types of teacher feedback and types of student revision in EFL writing courses. Proceedings of 2018 International Symposium on Teaching, Education, and Learning (ISTEL 2018), Seoul, South Korea.

Cheng, G., & Ng, W. S. (2018, April). Using an automated approach to classify EFL students' revisions of their academic writing. Proceedings of the International Conference on Education and Global Studies (IConEGS 2018), Osaka, Japan.

Cheng, G., Chwo, S.-M. G., Chen, J., Foung, D., Lam, V., & Tom, M. (2017, December). Automatic classification of teacher feedback and its potential applications for EFL writing. Proceedings of the 25th International Conference on Computers in Education (ICCE 2017). Christchurch, New Zealand.

Biography of Principal Investigator

Dr Gary Cheng is an Associate Professor of Department of Mathematics and Information Technology at The Education University of Hong Kong (EdUHK). Prior to joining the EdUHK, Dr Cheng held various positions (e.g. academic staff, educational designer, systems consultant) at several higher education institutions in Hong Kong. His research interests include IT in education: ePortfolio-mediated learning; computer programming education; online learning management system; e-assessment; and educational data mining.

Funding Source

General Research Fund