It is critical for higher education institutions to work on improvement of their teaching and learning strategy by examining feedback of students. Sentiment analysis (also known as opinion mining or emotion AI) refers to the use of natural language processing (NLP) and text analysis to systematically identify, extract and quantify states and subjective information. Transfer learning (TL) could be a ponder in machine learning centering on putting away information picked up whereas understanding one issue and applying it to a diverse but related issue. In this paper, we present the results from applying BERT, a transfer learning method for one of text classification problems. The model aims to predict state positive, negative, or neutral of an online course from students’ reviews. This result will be compared with the contributions of authors Kastrati et al. (2020). The results which using BERT are quite good (Accuracy 88.93%), giving us more hope for future research.
Sentiment Analysis of Students’ Reviews on Online Courses: A Transfer Learning Method
9 Views
7 Downloads