ACME: automated classification model for E-learning feedback

ABSTRACT

E-learning is the process of sharing knowledge out of the traditional classrooms through different online tools using internet. The availability and use of these tools are not easy for every student. Many institutions gather e-learning feedback to know the problems of students to improve their systems. In e-learning systems, typically a high volume of electronic feedback is received every day. In order to respond to feedback quickly and to address the issues raised by the stakeholders timely, it is desirable to provide an intelligent and automatic classification of the feedback. This study proposes a feedback classification model, named “ACME: Automated Classification Model for E-learning Feedback” to fulfill this need. The proposed model is capable of both sentiment analysis and category classification of the feedback. In this regard, feedback from 20,000 records has been collected from many online sources, such as social media platforms, surveys, and questionnaires. To build a baseline corpus, these feedbacks were analyzed and characterized in two dimensions, that is category and sentiment. The model achieved an accuracy of 98% and 99% by using a Random Forest and Decision Tree classifier, respectively.

KEYWORDS:

• E-Learning feedback
• sentiment analysis
• category classification
• student feedback classification
• traditional machine learning prediction
• deep learning classification techniques

Disclosure statement

No potential conflict of interest was reported by the author(s).

Notes

1 https://developers.google.com/.

2 https://developers.google.com/machine-learning/crash-course/classification/roc-and-auc.

Additional information

Notes on contributors

Soomaiya Hamid

Soomaiya Hamid received her MS in Computer Networks and Security from the National University of Computer and Emerging Sciences, Pakistan and MS in Software Engineering from the Department of Computer Science and Software Engineering, Jinnah University for Women, Pakistan. Her research areas include Cybersecurity, Software Defined Networks, Machine Learning, Human-Computer Interaction, Internet of Things, Big Data, and Cloud Computing.

Narmeen Zakaria Bawany

Narmeen Zakaria Bawany received her PhD in Computer Science from the National University of Computer and Emerging Sciences, Pakistan. She is currently working as a Professor and Dean, Faculty of Science at Jinnah University for Women, Pakistan. She has supervised many projects and had also received funding from Ignite (National Technology Fund, Pakistan) for her projects. Her research areas include Human Computer Interaction, Cloud Computing, Blockchain technology, Machine Learning, Cyber security, and Software Defined Networking. She has more than 40 publications in journals and conferences.