Analytical Framework for Binarized Response for Enhancing Knowledge Delivery System

The student feedback offer effective insight into their experience of knowledge transfer, routinely collected in academic institutions. However, the existing research literature lacks reporting whether the comments in education system are helpful or non-useful. Most of the existing works are limited to sentiment polarity computation only, and teacher evaluation is carried out without considering the aspects of the teaching. This study analyzes student comments and classifies comments as applicable and non-useful for the teacher scoring system. In the proposed research, the data considered is the student feedback collected from the teacher rating website. The study performed phase-by-phase text data modeling. First, exploratory analysis is carried out on the student feedback dataset to understand text data characteristics and features. Based on the exploratory analysis, appropriate steps are determined to perform preprocessing operations for data cleaning. Using natural language processing context, the study only focuses on removing stop words and common words that belong to both useful and non-useful contexts. BoW model is considered for features extraction, and two probabilistic supervised machine learning models are used for comment classification. The study outcome exhibits that Gaussian Naïve Bayes outperforms Multinominal Naïve Bayes in accuracy, precision, recall rate, and F1-score.

@article{S2021,
  title     = {Analytical Framework for Binarized Response for Enhancing Knowledge Delivery System},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {12},
  number    = {11},
  year      = {2021},
  publisher = {The Science and Information Organization},
  author    = {Chethan G S and Vinay S},
  doi       = {10.14569/IJACSA.2021.0121157},
  url       = {https://doi.org/10.14569/IJACSA.2021.0121157}
}