Cognitive knowledge-based model for adaptive feedback: A case in physics / Andrew Thomas Bimba

Andrew Thomas, Bimba (2019) Cognitive knowledge-based model for adaptive feedback: A case in physics / Andrew Thomas Bimba. PhD thesis, University of Malaya.

[img] PDF (The Candidate's Agreement)
Restricted to Repository staff only

Download (184Kb)
    [img] PDF (Thesis PhD)
    Restricted to Repository staff only until 31 December 2021.

    Download (1985Kb)


      In a computer-based learning environment, feedback is considered as one of the most effective factors which influence learning. Tailoring feedback according to student’s characteristics and other external parameters is a promising way to implement adaptation in computer-based learning environment. There is an increase in the implementation of adaptive feedback models, which focus on the relationship between adaptive feedback and learning gains. These literatures suggest that the complex relationship between feedback, task complexity, pedagogical principles and student’s characteristics affect the significance of feedback effects. Various knowledge modeling techniques for providing feedback in computer-based learning environments have been proposed. However, review findings indicate that the techniques used are static, involve a manual knowledge elicitation process, and depend highly on volatile expert’s knowledge. Thus, there is a need to ease this process with an autonomous and dynamic approach to knowledge representation in an adaptive feedback environment. In addition, current studies also have shown limited research on the effect of multiple adaptive feedback characteristics on students’ learning gains. Hence, this research aims to design and implement a model which autonomously acquire knowledge on multiple adaptive feedback characteristics and evaluate its effect on student’s learning gains. The proposed model is multi-disciplinary, however in this research the focus is on the Physics domain as a case study. The model uses the Cognitive Knowledge Base (CKB) to represent knowledge as a formal concept based on an Object-Attribute-Relation (OAR) model. This technique, allows the CKB to make an autonomous decision on the type of feedback provided. The proposed cognitive knowledge-based model provides an autonomous and dynamic representation of knowledge on adaptive feedback in a computer-based learning environment. This form of representation is achieved through the knowledge elicitation, knowledge bonding, and adaptive feedback algorithms. The model is evaluated based on the feedback it suggests to students while solving Physics problems. Experiments with 31 pre-university students divided into traditional feedback, no feedback, and adaptive feedback groups were carried out. The effect of the adaptive feedback provided was measured using the learning gains, normalised learning gains and ANCOVA. In comparing three experimental groups, students who were provided with adaptive feedback showed learning gains and normalized learning gains of 0.87 and 0.05 over the normal feedback group, with 0.97 and 0.07 over the non-feedback group. The results indicate a better learning gain for students in the adaptive feedback group and a significant improvement in student’s learning based on the ANCOVA analysis. This research provides an autonomous means of acquiring knowledge based on the proposed model, which represents the relationship between a single concept and multiple concepts. It also provides a tool for the provision of adaptive feedback in a computer-based learning environment which is beneficial to students, teachers, and educational instructors.

      Item Type: Thesis (PhD)
      Additional Information: Thesis (PhD) - Faculty of Computer Science & Information Technology, University of Malaya, 2019.
      Uncontrolled Keywords: Computer-based learning environment; Object-Attribute-Relation (OAR) model; Cognitive Knowledge Base (CKB); Cognitive; Pre-university students
      Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
      Divisions: Faculty of Computer Science & Information Technology
      Depositing User: Mr Mohd Safri Tahir
      Date Deposited: 19 May 2020 01:26
      Last Modified: 19 May 2020 01:26

      Actions (For repository staff only : Login required)

      View Item