Conference Proceeding Article
At theend of each course, students are required to give feedback on the course andinstructor. This feedback includes quantitative rating using Likert scale andqualitative feedback as comments. Such qualitative feedback can providevaluable insights in helping the instructor enhance the course content andteaching delivery. However, the main challenge in analysing the qualitativefeedback is the perceived increase in time and effort needed to manually processthe textual comments. In this paper, we provide an automated solution foranalysing comments, specifically extracting implicit suggestions from thestudents’ qualitative feedback comments. The implemented solution leveragesexisting text mining and data visualization techniques and comprises three stages namely datapre-processing, implicit suggestions extraction and visualization. We evaluatedour solution using student feedback comments from seven undergraduate corecourses taught at the School of Information Systems, Singapore ManagementUniversity. The experiments show that the proposed solution generatedsuggestions from the comments with the F-Score of 78.1%.
student feedback, teaching evaluation, implicit suggestions, text analytics, text mining, classification techniques
Digital Communications and Networking | Programming Languages and Compilers
Data Management and Analytics
Proceedings of 25th International Conference on Computers in Education (ICCE), Christchurch, New Zealand, 2017 December 4-8
City or Country
Christchurch, New Zealand
SHANKARARAMAN, Venky; GOTTIPATI, Swapna; and LIN, Jeff Rongsheng.
Extracting implicit suggestions from students’ comments – A text analytics approach. (2017). Proceedings of 25th International Conference on Computers in Education (ICCE), Christchurch, New Zealand, 2017 December 4-8. 1-9. Research Collection School Of Information Systems.
Available at: http://ink.library.smu.edu.sg/sis_research/3833
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.